© 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. 53987
    Prev
    Next
    INDEX
    Explanations

    code or phrase beginnings

    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
    うちに
    -0.87
     aik
    -0.76
    Embry
    -0.73
     Guth
    -0.73
    agents
    -0.72
     часу
    -0.72
    盥
    -0.72
    noinspection
    -0.72
     hamil
    -0.71
     pasal
    -0.70
    POSITIVE LOGITS
     union
    0.96
     readonly
    0.93
    toFixed
    0.88
    吟
    0.85
    Compiler
    0.85
    TypeScript
    0.85
    compiler
    0.85
     TypeScript
    0.84
    td
    0.83
    𝛾
    0.82
    Activations Density 0.015%

    No Known Activations