© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 16830
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.99
    h
    0.93
    f
    0.91
    b
    0.79
    av
    0.78
    i
    0.76
    r
    0.76
    m
    0.76
    p
    0.76
    j
    0.74
    POSITIVE LOGITS
     appeals
    0.69
     pleading
    0.66
     pleads
    0.63
     que
    0.61
     अपील
    0.58
     appeal
    0.58
     appealed
    0.57
     emocion
    0.54
     Appeals
    0.54
     vestiges
    0.54
    Activations Density 0.029%

    No Known Activations