© 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. 82842
    Prev
    Next
    INDEX
    Explanations

    religious, spiritual texts, chanting

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

    vector graphics, lists, or character names

    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
    建筑
    0.47
    框架
    0.46
    槛
    0.46
    激素
    0.45
    疮
    0.45
    bors
    0.42
    这种情况
    0.42
     ہوں۔
    0.42
    inp
    0.41
     kerajaan
    0.41
    POSITIVE LOGITS
     municipal
    0.56
    ’
    0.55
    О
    0.53
    Municipal
    0.52
    M
    0.52
    R
    0.51
    O
    0.51
    B
    0.50
     members
    0.50
     Букмекеры
    0.50
    Activations Density 0.000%

    No Known Activations