© 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. 34-GEMMASCOPE-RES-131K
    7. 57427
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

    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
     Ceramic
    -0.87
     この
    -0.85
     идеи
    -0.84
     _________
    -0.82
     lacquer
    -0.81
     endast
    -0.81
     Setting
    -0.80
    leetcode
    -0.80
     ______
    -0.79
    fread
    -0.79
    POSITIVE LOGITS
     regardless
    1.02
     new
    0.93
     actually
    0.90
     our
    0.89
    بندی
    0.84
     spurred
    0.82
     either
    0.80
     prompted
    0.79
     more
    0.79
     senso
    0.79
    Activations Density 0.037%

    No Known Activations