© 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. 153041
    Prev
    Next
    INDEX
    Explanations

    Acting President

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

    recommendations and goals

    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
    憫
    0.51
    irthday
    0.51
     Taq
    0.47
     即
    0.46
     Puj
    0.46
    ❧
    0.45
     apostila
    0.44
     Curr
    0.44
     Ingers
    0.44
     Noh
    0.44
    POSITIVE LOGITS
    <0x0D>
    0.52
     plen
    0.49
     cranes
    0.48
     دیوار
    0.47
     perched
    0.47
     раду
    0.46
     चढ़
    0.46
     निवास
    0.46
     boute
    0.46
     quarant
    0.46
    Activations Density 0.000%

    No Known Activations