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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 175
    Prev
    Next
    INDEX
    Explanations

    muffin man

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

    This neuron activates on individual punctuation marks and unicode symbols, especially those used in decorative text or text-based emoticons.

    oai_token-act-pair · gemini-2.5-flashTriggered by @ananthanv94
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    การ
    0.59
     العديد
    0.58
     Re
    0.55
     arguably
    0.55
     screening
    0.55
     many
    0.55
     highlights
    0.54
     more
    0.54
     some
    0.54
     headcount
    0.52
    POSITIVE LOGITS
     interposed
    0.67
    Observable
    0.66
    AspNetUser
    0.64
    vaient
    0.64
    issaient
    0.62
    áról
    0.59
    ását
    0.59
    groupId
    0.58
    perturb
    0.58
    Seite
    0.58
    Activations Density 0.000%

    No Known Activations