© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 13866
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    lnk
    0.66
     ln
    0.61
    只需要
    0.61
    VAS
    0.53
    summ
    0.52
     Stair
    0.52
     সঙ্ক
    0.52
    {~
    0.51
    ln
    0.51
     framing
    0.51
    POSITIVE LOGITS
    宠物
    0.60
    轮胎
    0.59
    帝国
    0.59
     excepción
    0.54
     जिनकी
    0.54
    чные
    0.54
    生地
    0.53
     bees
    0.52
    液体
    0.52
    年月日
    0.52
    Activations Density 0.000%

    No Known Activations