© 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. 108003
    Prev
    Next
    INDEX
    Explanations

    rights reserved, resource

    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
    Kimberly
    -0.77
     achten
    -0.76
    ome
    -0.69
    alumnos
    -0.69
    veness
    -0.68
    gui
    -0.68
    improve
    -0.67
     Chhattisgarh
    -0.67
    LAURA
    -0.67
    ;}
    -0.66
    POSITIVE LOGITS
     Eleventh
    0.81
     twelve
    0.81
     sixteen
    0.79
     seventeenth
    0.77
     Thirteenth
    0.73
     Seventeenth
    0.73
     Fourteenth
    0.72
     Sixteenth
    0.71
     дыха
    0.71
    xii
    0.69
    Activations Density 0.316%

    No Known Activations