© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99201
    Prev
    Next
    INDEX
    Explanations

    jQuery `this` selectors

    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
     even
    -1.88
     of
    -1.83
     but
    -1.82
     If
    -1.70
     lounging
    -1.58
     does
    -1.56
     takes
    -1.55
     to
    -1.54
     be
    -1.53
     allows
    -1.52
    POSITIVE LOGITS
    The
    1.75
    5
    1.73
    Specifically
    1.73
    Already
    1.70
    )
    1.69
    ᠊
    1.67
    ౮
    1.65
    8
    1.64
    the
    1.60
    飆
    1.60
    Activations Density 0.005%

    No Known Activations