© 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. 67391
    Prev
    Next
    INDEX
    Explanations

    independent variables and data

    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
    '
    -1.85
     ...
    -1.45
    ↵
    -1.44
     why
    -1.31
     '
    -1.27
     also
    -1.23
     понадоби
    -1.22
    ';
    -1.22
     how
    -1.20
     …
    -1.19
    POSITIVE LOGITS
    independent
    1.61
    翾
    1.52
    Each
    1.48
    譙
    1.48
     независи
    1.47
    ână
    1.46
    嵎
    1.44
    koszulka
    1.43
     integrados
    1.43
     effekt
    1.41
    Activations Density 0.041%

    No Known Activations