© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47293
    Prev
    Next
    INDEX
    Explanations

    spark ignited

    np_acts-logits-general · gemini-2.5-flash-lite

    process and generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turistas
    0.45
    ن
    0.42
    د
    0.42
    ر
    0.42
    ل
    0.42
     lakhs
    0.41
     opponents
    0.41
     cargas
    0.40
    码
    0.40
    ف
    0.40
    POSITIVE LOGITS
     緊急
    0.48
    িক্স
    0.46
     समिट
    0.45
    isa
    0.45
     उसका
    0.42
     उसको
    0.42
     particulier
    0.42
     उसे
    0.42
    jegyz
    0.42
    ambah
    0.42
    Activations Density 0.000%

    No Known Activations