© 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. 169493
    Prev
    Next
    INDEX
    Explanations

    In Proceedings

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

    AI-powered driver, historical figure

    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
     phenylalanine
    0.49
     Awakening
    0.44
     вклад
    0.43
    Inactive
    0.43
     extremamente
    0.43
     Firearms
    0.43
    <unused173>
    0.43
     விள
    0.42
     धमकी
    0.42
    %!
    0.42
    POSITIVE LOGITS
    зи
    0.52
    ли
    0.50
    λλ
    0.48
    บ้าน
    0.43
    ificat
    0.43
    zels
    0.43
    墟
    0.42
    ાઇ
    0.42
    ol
    0.42
    ardless
    0.42
    Activations Density 0.000%

    No Known Activations