Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 11815
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on content-bearing tokens (meaningful nouns/verbs/identifiers and keywords) rather than on common function words or punctuation.

    oai_token-act-pair · gpt-5-miniTriggered by @toaster
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-1b-it/resid_post
    Prompts (Dashboard)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SDI
    0.92
    ︠
    0.88
    苺
    0.87
    Ireland
    0.86
     आंकड़े
    0.85
     numArray
    0.85
     पलीनोमियल
    0.84
     ৷
    0.84
    Prescott
    0.84
     Ariz
    0.83
    POSITIVE LOGITS
    h
    0.77
     headspace
    0.68
     h
    0.67
    ૃત
    0.64
    เ
    0.59
     hinter
    0.59
     deep
    0.59
     v
    0.57
     k
    0.56
    若
    0.55
    Activations Density 0.000%

    No Known Activations