© 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. 159972
    Prev
    Next
    INDEX
    Explanations

    said, sins, causes, once, Europe

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

    creators, recycl, soccer, skin

    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
    [{
    0.48
    https
    0.47
     hôn
    0.44
     Trên
    0.43
     Nge
    0.42
    ရဲ့
    0.42
    🤣🤣
    0.42
     Bă
    0.42
    ui
    0.40
    <unused63>
    0.40
    POSITIVE LOGITS
    ারন
    0.47
    ष्टिक
    0.47
     manures
    0.47
    𐰺
    0.46
     کنند
    0.45
     otomatik
    0.44
     colds
    0.44
     விதை
    0.44
     بیم
    0.44
     игр
    0.44
    Activations Density 0.000%

    No Known Activations