© 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. 76151
    Prev
    Next
    INDEX
    Explanations

    developer paths

    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
     reflect
    -0.67
     nies
    -0.66
     surrendered
    -0.65
     FREE
    -0.65
     Czer
    -0.64
     dependable
    -0.63
    Equilibrium
    -0.63
     surrender
    -0.63
    打的
    -0.62
    nursing
    -0.62
    POSITIVE LOGITS
     ș
    0.73
    downarrow
    0.66
    Query
    0.66
    medad
    0.66
    bing
    0.66
    inda
    0.65
     tài
    0.65
    cicle
    0.65
     acque
    0.65
    ного
    0.64
    Activations Density 0.050%

    No Known Activations