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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9299
    Prev
    Next
    INDEX
    Explanations

    offers creative writing prompts

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

    This neuron detects colon tokens that introduce list items, section headings, or enumerated subsections.

    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_24_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
    Addition
    0.62
    Fight
    0.60
    ﺵ
    0.59
     вроде
    0.57
    Irish
    0.57
    Brazilian
    0.57
     такие
    0.56
    GetComponents
    0.56
     ಎಲ್ಲಾ
    0.56
    Shoes
    0.55
    POSITIVE LOGITS
     verbs
    0.61
     เอ่อ
    0.58
     moderately
    0.57
     incredibly
    0.54
    栆
    0.54
    -...
    0.53
    ًا
    0.53
    uose
    0.53
    <0x9B>
    0.52
     unbelievably
    0.52
    Activations Density 0.004%

    No Known Activations