© 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. 112720
    Prev
    Next
    INDEX
    Explanations

    All-American, All-State, All-SEC, All-Star

    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
    additional
    -2.06
     réfrig
    -1.97
    0
    -1.95
     evangé
    -1.80
     décès
    -1.79
    ’
    -1.77
    these
    -1.70
     mâle
    -1.70
    b
    -1.69
     decorativo
    -1.68
    POSITIVE LOGITS
     and
    2.06
    koning
    1.90
    ឬ
    1.83
    浤
    1.81
    lites
    1.70
     esperienza
    1.66
    𓆜
    1.66
    걍
    1.63
    ?}
    1.63
     on
    1.63
    Activations Density 0.004%

    No Known Activations