© 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. 75818
    Prev
    Next
    INDEX
    Explanations

    award basis pays

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

    run directly

    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
     lote
    0.51
     sinusitis
    0.50
     kerat
    0.50
     traumat
    0.48
    ’
    0.48
     Hospital
    0.47
     terapi
    0.46
     hospitalization
    0.46
     smog
    0.45
     disorientation
    0.45
    POSITIVE LOGITS
     Лю
    0.54
     ሌሎች
    0.52
     Andere
    0.49
    )_{\
    0.46
     كا
    0.44
    getParameters
    0.44
    getNumber
    0.44
     Жен
    0.44
     లె
    0.43
     Поли
    0.43
    Activations Density 0.000%

    No Known Activations