© 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. 158998
    Prev
    Next
    INDEX
    Explanations

    Americans or others

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

    analysis of historical texts, languages, okapi relatives, stairs, American culture, and philosophical introspection

    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
    ता
    0.48
     Secretaria
    0.46
     sekret
    0.45
    旬
    0.43
    :-
    0.42
     deras
    0.42
     rufis
    0.42
    ೇಳ
    0.42
    GRADE
    0.42
    ，
    0.42
    POSITIVE LOGITS
     όχι
    0.49
    }]$.
    0.46
     আমেরিকান
    0.44
     Americans
    0.43
     американ
    0.42
    กำลัง
    0.41
    تھی
    0.41
    γκε
    0.41
    ScrollBar
    0.41
     américaine
    0.41
    Activations Density 0.001%

    No Known Activations