© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15325
    Prev
    Next
    INDEX
    Explanations

    acknowledging common traits or difficulties

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on uncommon, low-frequency content words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    garbled or corrupted text that appears to be machine-generated or scraped web content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    specialized, technical-sounding terminology and formal nouns, especially those related to measurements, processes, or professional domains.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sess
    0.86
    ดำ
    0.86
    рения
    0.81
    callbacks
    0.76
     правительства
    0.75
     biochem
    0.75
    dens
    0.75
    saya
    0.74
    sterdam
    0.72
    descricao
    0.72
    POSITIVE LOGITS
     afferma
    0.75
     unu
    0.72
    지만
    0.68
     posti
    0.68
    곧
    0.68
     costitu
    0.67
     підприєм
    0.67
     promu
    0.67
     affirme
    0.67
     realtà
    0.67
    Activations Density 0.000%

    No Known Activations