© 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. 1940
    Prev
    Next
    INDEX
    Explanations

    tiny animals and objects

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

    This neuron detects user instructions asking the model to write a story about a specific subject (the subject noun in a "write me a story about X" prompt).

    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
    財務
    0.63
     वित्तीय
    0.59
    纰
    0.55
     fucked
    0.53
     ఆర్థిక
    0.53
     financially
    0.52
    経済
    0.52
     финансо
    0.50
    🔍
    0.49
     ಕ್ಷೇತ್ರ
    0.49
    POSITIVE LOGITS
     snout
    0.77
     tummy
    0.73
     feline
    0.65
     gourd
    0.61
     beak
    0.59
     pebbles
    0.59
     aventuras
    0.59
     nursery
    0.57
     yolk
    0.57
     tiny
    0.57
    Activations Density 0.307%

    No Known Activations