© 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. 199286
    Prev
    Next
    INDEX
    Explanations

    Syrian airspace

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

    recognizing issues and patterns

    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
    ПА
    0.50
    ка
    0.47
    falls
    0.46
     terrorists
    0.45
    digit
    0.44
     సమా
    0.43
     Himalayas
    0.43
     emperors
    0.43
    벤
    0.43
     pantry
    0.43
    POSITIVE LOGITS
     recurring
    0.52
    とっても
    0.46
    ’
    0.46
     deprecated
    0.45
     Grosso
    0.45
    торами
    0.45
     Dire
    0.43
    umatic
    0.43
    ordum
    0.43
     begon
    0.43
    Activations Density 0.000%

    No Known Activations