© 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. 171947
    Prev
    Next
    INDEX
    Explanations

    financial details

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

    association and relation prepositions

    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
     Magnet
    0.44
     Stars
    0.43
     Exper
    0.42
     Region
    0.42
     ”
    0.42
     Magistrates
    0.42
     saga
    0.42
     anisotropic
    0.41
     Homo
    0.41
     Tau
    0.41
    POSITIVE LOGITS
    ală
    0.57
    НІ
    0.56
    𝗱
    0.55
    𝗴
    0.55
    니
    0.54
    doesn
    0.53
    нову
    0.53
    ні
    0.52
    コンサート
    0.52
    лені
    0.52
    Activations Density 0.000%

    No Known Activations