© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 7055
    Prev
    Next
    INDEX
    Explanations

    dot notation access

    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
     kellett
    0.22
    <unused469>
    0.22
    homeini
    0.21
    <unused1827>
    0.20
    姏
    0.20
     hukuk
    0.20
    <unused368>
    0.19
    ו
    0.19
    <unused421>
    0.19
    <unused477>
    0.19
    POSITIVE LOGITS
    ['
    0.30
    ._
    0.30
    ["
    0.27
    ['_
    0.24
    .
    0.21
    '
    0.21
    .__
    0.21
     extrinsic
    0.20
     intrinsic
    0.20
    [
    0.20
    Activations Density 0.006%

    No Known Activations