© 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. 78970
    Prev
    Next
    INDEX
    Explanations

    numerical separators and digits

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

    yuan currency values

    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
    I
    1.19
    твы
    0.82
    Ihr
    0.81
    عمال
    0.72
    ج
    0.72
    িস্ট
    0.71
    Ins
    0.70
    িও
    0.70
    elog
    0.70
    InData
    0.70
    POSITIVE LOGITS
    over
    0.93
    i
    0.89
    of
    0.87
    ng
    0.86
    n
    0.85
    as
    0.82
    ran
    0.80
    ier
    0.79
    un
    0.78
    mie
    0.77
    Activations Density 0.147%

    No Known Activations