© 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. 103526
    Prev
    Next
    INDEX
    Explanations

    search

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

    production to pilot, reward to payout

    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
    iterate
    0.49
    痉
    0.45
    파일명
    0.44
    мб
    0.44
     empêcher
    0.42
    éraires
    0.41
     précéd
    0.41
    Ҭ
    0.41
    за
    0.40
     empê
    0.40
    POSITIVE LOGITS
     UP
    0.50
     EU
    0.48
     SMS
    0.48
    k
    0.47
     APPRO
    0.47
     ALPHA
    0.47
     attenuation
    0.46
     ČR
    0.46
     AMPL
    0.46
     OF
    0.46
    Activations Density 0.000%

    No Known Activations