© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69882
    Prev
    Next
    INDEX
    Explanations

    reflection and programming constructs

    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_34/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
     whofe
    -0.90
     الوز
    -0.82
    ängt
    -0.81
     Afric
    -0.77
     Lakh
    -0.75
     zincir
    -0.73
    cP
    -0.73
     PRINCIPLES
    -0.73
     Interpreter
    -0.72
    Embeddable
    -0.71
    POSITIVE LOGITS
    Obfusc
    0.86
    ระ
    0.82
     название
    0.77
     cor
    0.76
     madres
    0.70
    laying
    0.69
     Thai
    0.69
     tra
    0.69
    Thai
    0.69
     sabe
    0.68
    Activations Density 0.019%

    No Known Activations