© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12579
    Prev
    Next
    INDEX
    Explanations

    unacceptable, anger, complaints

    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
     shorthand
    0.47
     endow
    0.47
     spannend
    0.46
     evolutionary
    0.46
     गतिशील
    0.46
     :)
    0.46
     succeeds
    0.46
    OGRAPHY
    0.46
    有助于
    0.45
    暂
    0.45
    POSITIVE LOGITS
    😡
    0.88
    🤬
    0.86
     disgusting
    0.80
     refused
    0.78
     fiasco
    0.73
     complaints
    0.71
     complained
    0.71
     unacceptable
    0.71
     incompetent
    0.70
     incompetence
    0.70
    Activations Density 0.037%

    No Known Activations