© 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. 10814
    Prev
    Next
    INDEX
    Explanations

    business, home, services

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

    fields of study and professions

    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
     and
    0.36
    켐
    0.34
    ociation
    0.34
    न्दु
    0.33
     потім
    0.33
     করিলেন
    0.33
    atly
    0.32
     zatim
    0.32
    emes
    0.32
    樎
    0.32
    POSITIVE LOGITS
     alike
    0.63
     whatnot
    0.39
    alike
    0.35
     extraordinaire
    0.34
     Politiker
    0.33
     экономических
    0.32
    🤽
    0.31
    बीएसई
    0.31
     организаций
    0.31
     பொருட்க
    0.31
    Activations Density 0.296%

    No Known Activations