© 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. 62947
    Prev
    Next
    INDEX
    Explanations

    code, names, and technical terms

    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
    ukų
    -0.69
     vodi
    -0.68
    izon
    -0.68
     nouveautés
    -0.66
    lovakia
    -0.66
     logged
    -0.66
     clogging
    -0.65
    UPD
    -0.65
     rounding
    -0.64
    وصلات
    -0.64
    POSITIVE LOGITS
    guió
    0.90
     tari
    0.82
     PowerShell
    0.80
     bluza
    0.78
     tracer
    0.77
     terap
    0.77
    tracer
    0.77
     bicarbon
    0.75
     tient
    0.75
    Ƹ
    0.75
    Activations Density 0.015%

    No Known Activations