© 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. 213524
    Prev
    Next
    INDEX
    Explanations

    database cursor operations

    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
    ((
    0.47
    كذا
    0.39
    Turbo
    0.37
     LIST
    0.37
    几
    0.36
    中午
    0.36
     HOT
    0.36
     Vegetarian
    0.35
    妈
    0.35
     Trout
    0.35
    POSITIVE LOGITS
    প্রেম
    0.44
    ژه
    0.41
     ಮೇಲೆ
    0.40
    ders
    0.40
     반려동
    0.40
    asaan
    0.39
    con
    0.39
    itos
    0.39
     länge
    0.39
    assan
    0.39
    Activations Density 0.020%

    No Known Activations