© 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. 16830
    Prev
    Next
    INDEX
    Explanations

    pleading, appeal, plea

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

    appealing or pleading to others

    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
    a
    0.89
    f
    0.87
    h
    0.83
    b
    0.79
    z
    0.77
    m
    0.71
    p
    0.71
    лся
    0.70
    i
    0.69
    d
    0.69
    POSITIVE LOGITS
     pleading
    0.74
     pleads
    0.74
     plead
    0.66
     appeals
    0.60
     appeal
    0.54
     pleaded
    0.53
     excuse
    0.53
     plea
    0.53
     अपील
    0.53
     peels
    0.53
    Activations Density 0.023%

    No Known Activations