© 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. 191322
    Prev
    Next
    INDEX
    Explanations

    every candidate, another agreement, public expense

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

    understanding content types

    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
    Not in Any Lists

    No Comments

    Negative Logits
     र
    0.59
    urea
    0.55
    ets
    0.54
    iden
    0.54
    idea
    0.51
    री
    0.50
    म
    0.50
    ो
    0.50
    one
    0.48
    ip
    0.48
    POSITIVE LOGITS
    RefItem
    0.46
     উপরের
    0.45
     ఉంటాయి
    0.45
     činn
    0.45
    ായത്
    0.43
    кмекер
    0.43
     Traits
    0.43
     Items
    0.43
     الشريط
    0.42
    Etiam
    0.42
    Activations Density 0.001%

    No Known Activations