© 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. 233739
    Prev
    Next
    INDEX
    Explanations

    felt material

    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
    Emergency
    0.48
     Emergency
    0.48
     Nib
    0.46
    در
    0.43
    葶
    0.43
     masalah
    0.42
    ادی
    0.41
    सद
    0.41
     fehlen
    0.41
     Gasoline
    0.40
    POSITIVE LOGITS
     ಉತ್ಪ
    0.44
     ಪುಸ್ತಕ
    0.44
     ಖರೀ
    0.43
     ಮಾಡುತ್ತ
    0.43
     reformer
    0.42
     rookies
    0.42
     非
    0.42
     誕生日
    0.42
     राजे
    0.41
     秋冬
    0.41
    Activations Density 0.001%

    No Known Activations