© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10665
    Prev
    Next
    INDEX
    Explanations

    particularly notorious, description states, often softens

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

    This neuron responds to numeric or enumerated reference markers—e.g. verse/chapter numbers, list labels (a., b., c.), and other digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نشر
    0.63
    庥
    0.63
     Lately
    0.62
     பல்கலைக்கழக
    0.62
     опубли
    0.61
     Leider
    0.61
    ईआरटी
    0.60
     সত্যিকারের
    0.60
    🖕
    0.59
     collaborations
    0.58
    POSITIVE LOGITS
     here
    0.72
     notice
    0.68
     implied
    0.67
    cf
    0.65
    这里的
    0.65
     clause
    0.64
     cf
    0.61
     emphatic
    0.60
    impl
    0.60
     motif
    0.60
    Activations Density 0.161%

    No Known Activations