© 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. 13940
    Prev
    Next
    INDEX
    Explanations

    cobracorneal

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

    The neuron fires strongly on stray numeric‐looking tokens (long floating‐point numbers) scattered through the text.

    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
     требуют
    0.82
    ymmetry
    0.81
     ensue
    0.80
     hardened
    0.77
    вающей
    0.77
     требует
    0.77
     specify
    0.76
    蓥
    0.75
     tactic
    0.74
     requ
    0.73
    POSITIVE LOGITS
    Giov
    0.78
     masalah
    0.77
     aki
    0.76
     roten
    0.76
    inputId
    0.75
     laporan
    0.72
    堬
    0.71
    lossen
    0.70
    frontend
    0.70
    يري
    0.70
    Activations Density 0.000%

    No Known Activations