© 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. 128922
    Prev
    Next
    INDEX
    Explanations

    digit 9

    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
     tamamen
    -2.11
     asomb
    -2.06
     vuestro
    -1.97
    藹
    -1.80
     verdaderamente
    -1.80
     to
    -1.77
     évit
    -1.75
    渼
    -1.74
    hanno
    -1.74
    為に
    -1.73
    POSITIVE LOGITS
    e
    2.36
    ol
    2.09
    {
    2.08
    p
    2.03
     was
    1.98
    ⬯
    1.94
    </h3>
    1.91
    ’
    1.91
    d
    1.90
     различные
    1.84
    Activations Density 0.080%

    No Known Activations