© 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. 18397
    Prev
    Next
    INDEX
    Explanations

    keywords and categories

    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
     Assim
    0.46
     گھ
    0.43
     קי
    0.43
     células
    0.42
     Using
    0.42
     natthi
    0.42
     ਘ
    0.42
    Assim
    0.41
    unti
    0.41
     cells
    0.40
    POSITIVE LOGITS
    бот
    0.55
    рой
    0.52
    <0x89>
    0.50
    rlige
    0.48
    幌
    0.47
    жая
    0.46
    봅
    0.46
    ്
    0.46
    ель
    0.46
    zczeg
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.