© 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. 51927
    Prev
    Next
    INDEX
    Explanations

    UB, UC, UF, UH, U-Haul

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

    u letters and symbols

    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
    و
    0.94
    p
    0.79
    m
    0.78
    r
    0.73
    ס
    0.73
    st
    0.73
    ne
    0.72
    ו
    0.71
    ک
    0.68
    로
    0.67
    POSITIVE LOGITS
    .
    0.79
    arakhand
    0.69
     UH
    0.65
     UF
    0.65
    bilical
    0.64
     Ush
    0.64
     UB
    0.62
     cercanos
    0.62
     U
    0.61
    :
    0.60
    Activations Density 0.178%

    No Known Activations