© 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. 70022
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

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

    codes and notations

    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
     কাপড়
    0.49
     viande
    0.48
     salads
    0.46
     shops
    0.46
     belanja
    0.44
     খাবার
    0.44
    विभाग
    0.44
    廁
    0.44
    ショップ
    0.43
     totalPrice
    0.43
    POSITIVE LOGITS
     CNRS
    0.57
    w
    0.50
    2
    0.48
    5
    0.48
     CE
    0.46
     Bcl
    0.45
    d
    0.45
     II
    0.45
     demonstrable
    0.45
    s
    0.44
    Activations Density 0.002%

    No Known Activations