© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9613
    Prev
    Next
    INDEX
    Explanations

    code definitions and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     proffered
    0.35
     foaf
    0.35
    }.
    0.34
     ವೇಳೆ
    0.34
     uranyl
    0.34
    เนิน
    0.34
     litig
    0.34
     так
    0.33
     тако
    0.33
     basaltes
    0.32
    POSITIVE LOGITS
    author
    0.45
     Define
    0.42
    usepackage
    0.40
     создал
    0.39
     定义
    0.39
    set
    0.38
    import
    0.37
     F
    0.36
     Adventure
    0.36
     Nombre
    0.36
    Activations Density 0.125%

    No Known Activations