© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26970
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    ชม
    0.45
    Manuel
    0.44
    гій
    0.43
     डॉक्यूमेंट्री
    0.42
    馏
    0.41
    נג
    0.41
    ִ
    0.41
    กล่าว
    0.40
    艺
    0.40
    ริม
    0.40
    POSITIVE LOGITS
    varrho
    0.39
     Jung
    0.38
     V
    0.38
     contr
    0.38
     XIX
    0.36
    一年
    0.36
     X
    0.36
    beta
    0.36
    debug
    0.35
     N
    0.35
    Activations Density 0.002%

    No Known Activations