© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9558
    Prev
    Next
    INDEX
    Explanations

    trial leaderboards, bed heaters, shelf brackets, bridge decks, inspired t-shirts, stove installation, packers championships, terminal types

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

    presentations and outlines

    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
     sayıda
    0.35
     değişt
    0.32
     tratando
    0.31
    広が
    0.31
    ७
    0.30
    🚍
    0.30
     manifiesta
    0.29
     metrizable
    0.29
     அறிந்த
    0.29
     threx
    0.29
    POSITIVE LOGITS
    での
    0.36
     Video
    0.35
     R
    0.34
    に関する
    0.33
    への
    0.32
     Research
    0.32
     Study
    0.32
     E
    0.32
     Review
    0.32
     Tips
    0.32
    Activations Density 0.484%

    No Known Activations