© 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. 114146
    Prev
    Next
    INDEX
    Explanations

    specific following words

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

    matching code snippets

    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
    련
    0.52
    c
    0.51
    újo
    0.49
     motoc
    0.48
     fila
    0.47
    ي
    0.47
    ج
    0.47
     exploits
    0.46
     nią
    0.46
     filas
    0.46
    POSITIVE LOGITS
    clusively
    0.43
    枭
    0.41
    asign
    0.41
     offsetting
    0.41
    篌
    0.41
    hehe
    0.40
    asted
    0.40
     ಎರಡು
    0.40
    unez
    0.40
    太子
    0.40
    Activations Density 0.001%

    No Known Activations