© 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. 173371
    Prev
    Next
    INDEX
    Explanations

    citations and editors

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

    actions, content, and relationships

    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
    ینه
    0.46
     Matthew
    0.46
    িনিয়ার
    0.46
    厸
    0.45
    ribution
    0.44
    assuming
    0.44
     जंग
    0.43
     کرمان
    0.43
     میچ
    0.42
    aksud
    0.42
    POSITIVE LOGITS
     vl
    0.45
    ccncc
    0.45
     сы
    0.44
     intoler
    0.44
     surpluses
    0.43
     продукти
    0.42
     logements
    0.42
    숱
    0.42
    saldo
    0.42
     хуже
    0.42
    Activations Density 0.001%

    No Known Activations