© 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. 192548
    Prev
    Next
    INDEX
    Explanations

    dynamic object has upstream handle

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

    program constructs

    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
    bud
    0.43
    ever
    0.42
     Site
    0.41
    ście
    0.40
    pr
    0.40
    era
    0.39
    AppName
    0.39
    재
    0.39
    site
    0.39
    erm
    0.38
    POSITIVE LOGITS
     myself
    0.46
     своими
    0.42
    変化
    0.40
     sibling
    0.40
     negotiate
    0.39
     þis
    0.39
    ামী
    0.38
     خودش
    0.38
    (){}
    0.38
     този
    0.37
    Activations Density 0.002%

    No Known Activations