© 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. 213309
    Prev
    Next
    INDEX
    Explanations

    calculate cost, capture pages, open rates

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

    estimate, contract, Russia, arrive, contains

    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
    幸
    0.49
    вейца
    0.48
    サスカ
    0.48
    ტერ
    0.47
    سع
    0.46
    耶路撒
    0.46
    بق
    0.46
    вело
    0.45
     Хер
    0.45
     bisogno
    0.45
    POSITIVE LOGITS
    1
    0.55
     for
    0.52
    2
    0.52
    ed
    0.51
    ...)
    0.50
    a
    0.48
    "]
    0.46
    }".
    0.46
     Table
    0.46
     Trying
    0.45
    Activations Density 0.001%

    No Known Activations