© 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. 57820
    Prev
    Next
    INDEX
    Explanations

    static analysis tools

    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
    sinh
    -0.83
    izmus
    -0.78
    clerview
    -0.77
    codable
    -0.77
    ensing
    -0.76
     imm
    -0.76
    encies
    -0.75
    zczegól
    -0.75
    enet
    -0.75
     hist
    -0.74
    POSITIVE LOGITS
     static
    1.48
     tool
    1.40
     tools
    1.35
     automated
    1.31
     Static
    1.27
    static
    1.23
     automatic
    1.19
    Static
    1.17
    tool
    1.08
    automatic
    1.06
    Activations Density 0.057%

    No Known Activations