© 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. 39532
    Prev
    Next
    INDEX
    Explanations

    what to, [effect, search form

    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
     and
    -3.03
     for
    -1.80
    ynb
    -1.75
     This
    -1.73
    nteral
    -1.69
     based
    -1.66
    ").
    -1.66
    ArrowToggle
    -1.64
     If
    -1.62
    resizingMask
    -1.62
    POSITIVE LOGITS
    L
    2.05
    N
    1.94
     samband
    1.85
    そんなに
    1.83
    various
    1.77
    majority
    1.77
    Reducing
    1.75
    ﾕ
    1.71
    Technically
    1.71
    だいぶ
    1.70
    Activations Density 0.000%

    No Known Activations