© 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. 100340
    Prev
    Next
    INDEX
    Explanations

    ages and numbers

    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
     the
    -1.23
     slår
    -1.20
     Formerly
    -1.18
     koel
    -1.14
    बर
    -1.11
     but
    -1.11
    terea
    -1.10
     väljer
    -1.09
     comprends
    -1.08
     jouet
    -1.07
    POSITIVE LOGITS
     лучший
    1.15
     "/";
    1.11
    I
    1.09
    ()}>
    1.09
     радость
    1.06
     huellas
    1.04
    —¡
    1.03
     my
    1.03
    Occurred
    1.02
     사이
    1.02
    Activations Density 0.022%

    No Known Activations