© 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. 38985
    Prev
    Next
    INDEX
    Explanations

    Honorable or Hon. 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
     großen
    -2.70
     neuen
    -2.63
     nuevos
    -2.56
    ,’”
    -2.56
     When
    -2.48
     cuando
    -2.44
    ',
    -2.39
    </h3>
    -2.36
     Pokud
    -2.36
     kleinen
    -2.34
    POSITIVE LOGITS
     vernac
    2.69
     IBRARY
    2.64
    淠
    2.63
     interi
    2.50
     ACTIVITY
    2.41
     gita
    2.41
    Hon
    2.39
    fordable
    2.38
     抠
    2.38
     階段
    2.36
    Activations Density 0.004%

    No Known Activations