© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249057
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases or medical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ન્સ
    0.48
     altercation
    0.48
    行った
    0.46
     オール
    0.45
    奄
    0.45
     інших
    0.45
    エスト
    0.44
     общего
    0.44
    队伍
    0.44
     ステン
    0.44
    POSITIVE LOGITS
    COPY
    0.47
    px
    0.46
    fantastic
    0.43
    /,
    0.42
    :,
    0.42
    Contents
    0.41
    in
    0.41
    ,}$
    0.41
    ப்பும்
    0.40
    \";
    0.39
    Activations Density 0.001%

    No Known Activations