© 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. 217945
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    research about emerging tech

    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
     품
    0.44
     Grund
    0.44
    golang
    0.44
    fmt
    0.43
    Odd
    0.43
    новый
    0.42
    medallas
    0.42
    Grund
    0.42
    in
    0.41
     SEQ
    0.41
    POSITIVE LOGITS
     เช่น
    0.51
     nk
    0.48
     zw
    0.47
    どうか
    0.47
    ଓ
    0.47
     ludzi
    0.46
     niz
    0.45
     להת
    0.44
     surveys
    0.43
     zina
    0.43
    Activations Density 0.001%

    No Known Activations