© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 951
    Prev
    Next
    INDEX
    Explanations

    book titles and guides

    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
    )
    0.35
    ers
    0.34
    (
    0.32
     on
    0.31
    and
    0.30
    2
    0.30
     (
    0.30
    5
    0.30
    are
    0.29
    -
    0.29
    POSITIVE LOGITS
    <unused619>
    0.35
    <unused193>
    0.34
    <unused624>
    0.34
     maneu
    0.34
    ير
    0.34
    ഷ്ട്ര
    0.33
    اونلوډ
    0.33
    <unused616>
    0.33
    راهيم
    0.33
    <unused591>
    0.33
    Activations Density 0.000%

    No Known Activations