© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212894
    Prev
    Next
    INDEX
    Explanations

    multilingual understanding, dates, gaming, hashes, entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ശി
    0.38
    Comprehensive
    0.38
    dracht
    0.38
    በት
    0.38
    폭
    0.38
     Gewalt
    0.38
    Germ
    0.38
    ⴼ
    0.38
    withdraw
    0.37
    Complete
    0.36
    POSITIVE LOGITS
    ڃ
    0.39
    [{
    0.38
    nt
    0.38
    ieden
    0.38
    erts
    0.38
     Christendom
    0.38
     NT
    0.37
    axes
    0.37
     Bleu
    0.37
     Garnier
    0.36
    Activations Density 0.034%

    No Known Activations