© 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. 10-GEMMASCOPE-RES-131K
    7. 59201
    Prev
    Next
    INDEX
    Explanations

    too

    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_10/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
    lossians
    -2.77
    ⃢
    -2.67
    ࿊
    -2.66
    lgari
    -2.53
    蜕
    -2.52
    罴
    -2.48
     of
    -2.39
    
    -2.36
     teh
    -2.34
    ႐
    -2.33
    POSITIVE LOGITS
    that
    3.27
    The
    2.78
    That
    2.59
    
    2.58
    在你
    2.53
    糴
    2.45
     fühlte
    2.42
    说是
    2.34
    owią
    2.30
    他
    2.30
    Activations Density 0.017%

    No Known Activations