© 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. 79453
    Prev
    Next
    INDEX
    Explanations

    .js files and optimizations

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

    javascript module file paths

    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
    when
    0.45
    ounter
    0.44
    Shan
    0.42
    ≔
    0.42
     Fundación
    0.40
    ázquez
    0.40
    estell
    0.40
    fänger
    0.40
    ASH
    0.40
    ->
    0.39
    POSITIVE LOGITS
     ה
    0.50
    מ
    0.50
     מי
    0.49
    བ
    0.49
     ล
    0.46
     о
    0.45
     ഡി
    0.44
     ಇ
    0.44
     Қ
    0.44
    ก
    0.43
    Activations Density 0.000%

    No Known Activations