© 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. 48503
    Prev
    Next
    INDEX
    Explanations

    offer, help, or, for

    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
     コン
    0.49
     ジ
    0.49
    ATUS
    0.47
     ウ
    0.47
     ク
    0.45
     エネルギー
    0.44
     精
    0.43
     および
    0.43
     マイ
    0.42
     証明
    0.42
    POSITIVE LOGITS
    蜷
    0.46
     equivale
    0.45
     amist
    0.45
    freund
    0.45
    verw
    0.45
    也会
    0.44
    ]-\
    0.43
    可能会
    0.43
    \
    0.42
    <=>
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.