© 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. 63469
    Prev
    Next
    INDEX
    Explanations

    code syntax or separators

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

    legal license text

    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
     ενεργ
    0.49
    u
    0.45
    NORE
    0.44
     начин
    0.43
     λειτουργ
    0.43
     ਕਰਨ
    0.43
     மறு
    0.43
    विधा
    0.43
    ặp
    0.42
     энергети
    0.42
    POSITIVE LOGITS
     stays
    0.47
    ной
    0.47
     Hein
    0.46
    gera
    0.45
    м
    0.45
    ۰
    0.45
    тою
    0.44
     Saul
    0.44
     portrays
    0.44
    ך
    0.43
    Activations Density 0.000%

    No Known Activations