© 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. 75791
    Prev
    Next
    INDEX
    Explanations

    food and negative outcomes

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

    can configure or replace

    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
     vantagens
    0.49
    ೮
    0.48
     ENGINEER
    0.46
     चित्रों
    0.46
     ಅವಕಾಶ
    0.45
     rigging
    0.44
     justifications
    0.44
     Considering
    0.44
    distanceArray
    0.44
    負担
    0.44
    POSITIVE LOGITS
    2
    0.59
     or
    0.51
     of
    0.48
    IN
    0.48
    Market
    0.47
    Comm
    0.47
    Char
    0.45
     fork
    0.45
    komm
    0.44
    Uber
    0.44
    Activations Density 0.000%

    No Known Activations