© 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. 204806
    Prev
    Next
    INDEX
    Explanations

    downloading, saving, printing

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

    importance and factors for income

    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
     ALLEN
    0.46
     Beg
    0.46
    線性
    0.46
     Ball
    0.46
     Coinbase
    0.44
    詢
    0.44
     Balashov
    0.44
     Anders
    0.44
     Allen
    0.43
     Lane
    0.43
    POSITIVE LOGITS
    discovered
    0.50
    ሖ
    0.48
    یدی
    0.46
     egregious
    0.45
    wać
    0.45
     ढंग
    0.45
    sufficient
    0.45
    spent
    0.44
    orar
    0.44
    orben
    0.44
    Activations Density 0.000%

    No Known Activations