© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40241
    Prev
    Next
    INDEX
    Explanations

    served as

    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
    🪆
    -2.08
     mehrm
    -2.03
    ších
    -2.00
     höheren
    -1.93
    ػ
    -1.91
    何故
    -1.91
    幾天
    -1.90
     οποίο
    -1.88
    They
    -1.88
     gelungen
    -1.88
    POSITIVE LOGITS
     a
    3.41
     in
    2.28
    D
    1.83
     also
    1.80
    </h1>
    1.77
    L
    1.67
    on
    1.66
    是
    1.61
     an
    1.61
     here
    1.59
    Activations Density 0.010%

    No Known Activations