© 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. 104161
    Prev
    Next
    INDEX
    Explanations

    endings

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

    non-latin scripts

    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
     海外
    0.51
    dets
    0.51
     আবহ
    0.48
    ractors
    0.48
    international
    0.46
    বা
    0.46
    ‌آ
    0.46
     ﺍ
    0.46
    oretically
    0.46
    ‌هایی
    0.45
    POSITIVE LOGITS
     conco
    0.48
    чи
    0.43
     hơn
    0.42
    Ри
    0.42
    جي
    0.41
    }+(
    0.41
    }+\
    0.40
     indicó
    0.40
     rép
    0.39
    бо
    0.38
    Activations Density 0.006%

    No Known Activations