© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106793
    Prev
    Next
    INDEX
    Explanations

    action progression or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    离开
    -0.82
    scanf
    -0.80
    spieler
    -0.79
    owań
    -0.78
    ۸
    -0.77
    chrome
    -0.76
     レストラン
    -0.75
    SCAN
    -0.75
     bia
    -0.74
    bieron
    -0.74
    POSITIVE LOGITS
     went
    4.50
     goes
    3.52
     go
    3.09
     going
    2.81
    Went
    2.72
    went
    2.56
    ไป
    2.56
     Went
    2.50
     WENT
    2.31
    Going
    2.19
    Activations Density 0.064%

    No Known Activations