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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8094
    Prev
    Next
    INDEX
    Explanations

    angles, surfing, RPM, shape

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

    The neuron strongly flags uncommon or domain‐specific tokens—especially proper names and otherwise rare words.

    oai_token-act-pair · o4-miniTriggered 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
    '
    1.25
    icular
    0.82
    ème
    0.75
    icking
    0.74
    ryt
    0.73
    🥺
    0.73
    接下来
    0.70
     אבל
    0.70
    itter
    0.69
    大家
    0.68
    POSITIVE LOGITS
     нередко
    0.98
     ଓ
    0.87
     လက်
    0.85
     လ
    0.83
     Constituição
    0.83
     ရ
    0.82
     muros
    0.82
     versão
    0.82
     utilização
    0.82
    cible
    0.81
    Activations Density 0.000%

    No Known Activations