© 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. 102908
    Prev
    Next
    INDEX
    Explanations

    released order market surveys

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

    Meaning, customs, hide, compile

    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
     are
    0.51
    ;
    0.50
     $
    0.50
     your
    0.49
     so
    0.49
     intolerable
    0.49
     unacceptable
    0.49
     currently
    0.49
     organisms
    0.48
     objectionable
    0.48
    POSITIVE LOGITS
     hatırl
    0.55
    帮
    0.55
    ग्ध
    0.52
     결혼
    0.51
     दोन
    0.50
    veriş
    0.49
    茶叶
    0.48
    aną
    0.48
     zakoń
    0.48
    arlık
    0.47
    Activations Density 0.001%

    No Known Activations