© 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. 66982
    Prev
    Next
    INDEX
    Explanations

    technical identifiers

    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
    (!__
    -1.64
     ekran
    -1.59
    昞
    -1.56
     reklama
    -1.50
     تجهیزات
    -1.50
     čase
    -1.46
    ᕱ
    -1.45
     privacidad
    -1.45
     accesorios
    -1.41
    髄
    -1.40
    POSITIVE LOGITS
     What
    1.86
    What
    1.83
     Unless
    1.73
     what
    1.70
    There
    1.68
     Occasionally
    1.55
    there
    1.55
     Rather
    1.54
    Rather
    1.50
     Although
    1.45
    Activations Density 0.058%

    No Known Activations