© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79830
    Prev
    Next
    INDEX
    Explanations

    return, super, regulator, if, Below, comScore, Analysis, xml

    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_22/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
    ﯿ
    -1.04
    鏽
    -0.97
     resultat
    -0.97
    の元
    -0.96
    methane
    -0.94
    ituaries
    -0.94
    贄
    -0.92
    zése
    -0.91
     olympique
    -0.91
    ళ్
    -0.90
    POSITIVE LOGITS
     each
    1.07
     every
    0.93
     but
    0.89
     only
    0.86
    Each
    0.83
     possibly
    0.82
    可能的
    0.80
     arising
    0.79
     prox
    0.78
     or
    0.77
    Activations Density 0.004%

    No Known Activations