© 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. 31583
    Prev
    Next
    INDEX
    Explanations

    Michel Guy, nice pop, New Hampshire

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

    universe, revenue, amount, surplus

    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
    Morris
    0.48
     VARCHAR
    0.47
    ة
    0.46
    概念
    0.46
     টেলিগ্রাফ
    0.45
     Гульнявыя
    0.44
    sexy
    0.44
    ła
    0.44
    پ
    0.44
    ijn
    0.43
    POSITIVE LOGITS
     contamin
    0.52
     Gentiles
    0.52
     persegi
    0.47
    的東西
    0.47
     שם
    0.46
    เพราะ
    0.46
     spleen
    0.45
    लाब
    0.45
     supaya
    0.44
     בכל
    0.44
    Activations Density 0.000%

    No Known Activations