© 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. 57548
    Prev
    Next
    INDEX
    Explanations

    xhtml doctype declarations 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
    唾
    -0.73
    Questionnaire
    -0.69
     crí
    -0.68
    Objec
    -0.68
    Marathon
    -0.68
     rally
    -0.66
     Amerik
    -0.65
    tych
    -0.65
     colectivos
    -0.64
    bodies
    -0.64
    POSITIVE LOGITS
     Unterlagen
    0.69
    zeugung
    0.69
    UNIT
    0.68
     Trow
    0.68
     Reed
    0.68
    ActionEvent
    0.67
     GRID
    0.66
     parsed
    0.65
    ས།
    0.64
    parse
    0.63
    Activations Density 0.087%

    No Known Activations