© 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. 121232
    Prev
    Next
    INDEX
    Explanations

    events and homes

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

    resistance cell, hidden payments, wealth of

    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
    徒歩
    0.52
    塊
    0.46
    年齢
    0.45
    盏
    0.44
    ボリューム
    0.43
    salaryfrom
    0.43
    フレーム
    0.42
    컬
    0.42
    ца
    0.41
    hattis
    0.41
    POSITIVE LOGITS
     livre
    0.55
     raisons
    0.49
     remon
    0.47
     bearbeitet
    0.47
     Polyp
    0.47
     daimyo
    0.46
     bargaining
    0.46
     tutela
    0.46
     राख
    0.45
     libre
    0.45
    Activations Density 0.001%

    No Known Activations