© 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. 177304
    Prev
    Next
    INDEX
    Explanations

    extremely strong

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

    technical leader design

    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
     $=
    0.46
    rda
    0.45
     kilo
    0.44
     $
    0.43
     $'
    0.43
    自助
    0.43
    র্জাতিক
    0.43
    rét
    0.43
    距
    0.42
     কের
    0.42
    POSITIVE LOGITS
     выра
    0.47
     consigned
    0.47
     summoned
    0.46
     отправи
    0.45
     лекар
    0.44
     thinkers
    0.44
     nebul
    0.44
     симво
    0.44
     weaknesses
    0.43
     futuros
    0.43
    Activations Density 0.001%

    No Known Activations