© 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. 199326
    Prev
    Next
    INDEX
    Explanations

    however, not

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

    RPE 7-8

    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
    Not in Any Lists

    No Comments

    Negative Logits
     فوج
    0.47
    HQ
    0.42
     洋
    0.41
     as
    0.41
     And
    0.41
    Ae
    0.40
    aided
    0.40
     string
    0.39
     extension
    0.39
    QL
    0.39
    POSITIVE LOGITS
     cadrul
    0.49
     достига
    0.49
    > </
    0.47
    ษา
    0.46
     čty
    0.46
    ذی
    0.45
     doua
    0.44
     Функция
    0.44
     ikinci
    0.44
     पुस्तक
    0.44
    Activations Density 0.000%

    No Known Activations