© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34017
    Prev
    Next
    INDEX
    Explanations

    File constructor

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

    class names followed by parentheses

    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
    centric
    0.48
    ಪ
    0.42
    kien
    0.38
    inness
    0.38
    aughey
    0.37
    advised
    0.37
    ienced
    0.37
     Erwin
    0.36
    พิมพ์
    0.36
    UG
    0.36
    POSITIVE LOGITS
    (){}
    0.52
     neumáticos
    0.45
    룹
    0.44
    ющиеся
    0.41
    ლებელია
    0.39
    вей
    0.38
     jaki
    0.37
     जै
    0.37
    лые
    0.37
    鳇
    0.37
    Activations Density 0.000%

    No Known Activations