© 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. 127637
    Prev
    Next
    INDEX
    Explanations

    8 or S-cd

    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
    耵
    -1.60
    ;</
    -1.58
     siè
    -1.48
    ing
    -1.45
     پنجم
    -1.44
    WHILE
    -1.43
     reposer
    -1.42
    ;.
    -1.41
     цветы
    -1.41
     is
    -1.38
    POSITIVE LOGITS
     eliminate
    1.59
     “
    1.52
     nuovamente
    1.34
     describe
    1.31
    全員
    1.29
     Both
    1.27
     anarchist
    1.26
     provoke
    1.25
     explore
    1.24
    ？』
    1.24
    Activations Density 0.010%

    No Known Activations