© 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. 15284
    Prev
    Next
    INDEX
    Explanations

    mathematical functions satisfying conditions

    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
    
    -2.50
     atendido
    -2.34
    geſ
    -2.31
     lazos
    -2.25
     orígenes
    -2.25
     Diputados
    -2.22
    ዡ
    -2.13
     rodeado
    -2.08
     $^{\
    -2.06
     aportes
    -2.06
    POSITIVE LOGITS
    s
    2.98
    *
    2.86
    (
    2.77
    —
    2.33
    or
    2.31
    “
    2.30
     that
    2.23
    You
    2.22
    /
    2.20
     “
    2.19
    Activations Density 0.004%

    No Known Activations