© 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. 104877
    Prev
    Next
    INDEX
    Explanations

    kids or pupils

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

    protagonists, history, doctrine, surreal numbers

    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
    ﺘ
    0.56
    П
    0.52
    Ľ
    0.50
    ТЕ
    0.49
     સફળ
    0.49
     ડિઝાઇન
    0.48
     эксплуатации
    0.47
    Պ
    0.46
    ZIONE
    0.46
    ÇÃO
    0.45
    POSITIVE LOGITS
    renched
    0.56
     chores
    0.54
     inns
    0.52
    andered
    0.52
     Ains
    0.51
     billets
    0.50
     iced
    0.49
    oworld
    0.48
     Iceland
    0.48
     linen
    0.48
    Activations Density 0.000%

    No Known Activations