© 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. 101412
    Prev
    Next
    INDEX
    Explanations

    He said

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

    frequency and networks

    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
    тий
    0.48
     HPC
    0.47
    й
    0.46
    مود
    0.45
    ल्या
    0.44
    лығы
    0.44
    тера
    0.44
    *[
    0.44
     virial
    0.43
    ശാസ്ത്ര
    0.43
    POSITIVE LOGITS
     সাধারণ
    0.56
    ark
    0.46
     পদ্ধতির
    0.46
     Jeter
    0.45
    淅
    0.45
     মিন
    0.45
     সাধারন
    0.44
    ্রেক
    0.44
     அழு
    0.44
     Suck
    0.44
    Activations Density 0.002%

    No Known Activations