© 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. 58687
    Prev
    Next
    INDEX
    Explanations

    mechanical parts, sales, sports teams

    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
    鵟
    -2.91
    樒
    -2.81
    鱨
    -2.55
    筇
    -2.52
    𓍊
    -2.48
    䊊
    -2.44
    
    -2.44
    裥
    -2.42
     wunderbar
    -2.41
    妺
    -2.41
    POSITIVE LOGITS
    U
    3.25
    Q
    2.88
    B
    2.88
    T
    2.67
    section
    2.67
    G
    2.67
    F
    2.63
    R
    2.45
    ’
    2.45
    ization
    2.44
    Activations Density 0.007%

    No Known Activations