© 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. 43330
    Prev
    Next
    INDEX
    Explanations

    allows, okay, roadmap, prioritizing

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

    The neuron lights up on important topic-bearing content words (key nouns and verbs) that signal main concepts in explanatory or definitional text.

    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
    1
    0.43
    5
    0.43
    2
    0.41
     inalámb
    0.41
    ποι
    0.40
    Wrapped
    0.39
     cinco
    0.39
     podían
    0.39
    3
    0.39
     সংস্ক
    0.38
    POSITIVE LOGITS
    য়াছে
    0.47
    കര
    0.45
    
    0.45
    lof
    0.44
     Haller
    0.43
     ایسا
    0.43
    rives
    0.41
     odstr
    0.41
    落在
    0.40
    ){//
    0.40
    Activations Density 0.003%

    No Known Activations