© 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. 25479
    Prev
    Next
    INDEX
    Explanations

    Okay, ideas, themes

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

    This neuron detects user requests or planning/intent phrases—tokens that express asking for help, wanting/deciding to do something, or otherwise requesting assistance (e.g., "I need help", "determine", "want to write").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     在
    0.43
     BufferedWriter
    0.42
     Notwithstanding
    0.41
     and
    0.39
     Vys
    0.38
     HCl
    0.38
    C
    0.37
     precise
    0.37
     每
    0.37
    べて
    0.36
    POSITIVE LOGITS
     themes
    0.84
    themes
    0.75
     temas
    0.73
     choisi
    0.70
     Themes
    0.69
     thème
    0.68
    Themes
    0.67
     idées
    0.66
     Ideen
    0.65
     темы
    0.64
    Activations Density 0.275%

    No Known Activations