© 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. 59325
    Prev
    Next
    INDEX
    Explanations

    vice president titles

    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
    蛲
    -2.08
     certamente
    -1.68
     (...
    -1.61
     améli
    -1.59
    ˕
    -1.56
    authorized
    -1.54
     resistenza
    -1.52
     emitir
    -1.52
    鶺
    -1.51
    狆
    -1.50
    POSITIVE LOGITS
    '
    2.64
     for
    2.02
     of
    1.89
     with
    1.76
    z
    1.59
     at
    1.58
    i
    1.53
     under
    1.51
    From
    1.48
    there
    1.45
    Activations Density 0.008%

    No Known Activations