© 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. 66810
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

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

    economic sectors

    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
    édération
    0.45
     >;
    0.44
    lets
    0.42
     তাকিয়ে
    0.42
    emia
    0.42
     physiologically
    0.42
    cik
    0.41
    ème
    0.41
     Marken
    0.41
    et
    0.41
    POSITIVE LOGITS
    ప్త
    0.55
    Vectors
    0.47
    Exponent
    0.47
    Ⴀ
    0.47
    近平
    0.46
    踐
    0.43
    します
    0.43
    форми
    0.43
    ποτε
    0.43
    칸
    0.42
    Activations Density 0.002%

    No Known Activations