© 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. 57112
    Prev
    Next
    INDEX
    Explanations

    code comments and URLs

    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
    OpCode
    -0.69
    oray
    -0.68
     BUN
    -0.67
     sessile
    -0.67
     Glenn
    -0.66
    ".$_
    -0.66
    funcion
    -0.66
     przeprowad
    -0.66
    aldo
    -0.65
    grill
    -0.65
    POSITIVE LOGITS
     Dialogue
    0.75
    NACIONAL
    0.72
     Fold
    0.70
    hove
    0.68
     cleaned
    0.67
    籍
    0.67
     Vocational
    0.66
    Buenos
    0.66
    Driver
    0.65
     gesuchten
    0.65
    Activations Density 0.044%

    No Known Activations