© 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. 160933
    Prev
    Next
    INDEX
    Explanations

    awards and qualifications

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

    Frames, countries, commitments, skill

    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
     embro
    0.52
     contemplate
    0.46
     pondering
    0.46
     disbursements
    0.46
    traction
    0.45
    ନ୍ଦ
    0.45
    뤽
    0.44
    통령
    0.44
     trillions
    0.43
    декс
    0.43
    POSITIVE LOGITS
     クリア
    0.46
     und
    0.46
     nélkül
    0.46
    fb
    0.45
     Fauna
    0.45
     linh
    0.45
     här
    0.44
     Favourite
    0.43
     invariant
    0.43
     as
    0.43
    Activations Density 0.001%

    No Known Activations