© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183198
    Prev
    Next
    INDEX
    Explanations

    automotive parts

    np_acts-logits-general · gemini-2.5-flash-lite

    entities and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    𝐁
    0.46
     grille
    0.45
     crackers
    0.45
     nhờ
    0.44
    桠
    0.43
    泰
    0.43
    <unused967>
    0.42
    麴
    0.42
     rắn
    0.42
    厭
    0.41
    POSITIVE LOGITS
    n
    0.47
    :");
    0.46
     bankrupt
    0.46
     Gestaltung
    0.45
    emptyDict
    0.44
    ci
    0.44
    altung
    0.43
    =",
    0.43
    pcion
    0.43
    :
    0.42
    Activations Density 0.001%

    No Known Activations