© 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. 41-GEMMASCOPE-2-RES-262K
    7. 6389
    Prev
    Next
    INDEX
    Explanations

    CSI, Arsi, Cosori, Assi, Forti, rsi, HSI

    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_all/layer_41_width_262k_l0_big
    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
    iaxial
    0.58
    ن
    0.57
    িপ
    0.54
    യുള്ള
    0.54
    filament
    0.53
    ক্র
    0.52
    functional
    0.52
    ILL
    0.51
    ‌కు
    0.50
    фектив
    0.49
    POSITIVE LOGITS
    깐
    0.83
    ゅう
    0.71
    ya
    0.70
    ños
    0.66
    yeh
    0.65
    ğinde
    0.63
    ņš
    0.63
    ye
    0.61
    ̇
    0.58
    યા
    0.58
    Activations Density 0.043%

    No Known Activations