© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    column, list, model, LLM type

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

    The neuron fires on words that express quantities or counts—e.g. number words (“two,” “three”) and approximate quantifiers (“almost”).

    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
    чёт
    0.73
     период
    0.71
    柇
    0.71
    ปก
    0.70
     період
    0.70
     बढ़ोतरी
    0.68
    Jab
    0.67
    Divine
    0.66
    <0xB1>
    0.66
    lü
    0.66
    POSITIVE LOGITS
     formality
    0.73
     formalities
    0.72
     comedy
    0.69
     Companies
    0.68
     dieses
    0.68
     toho
    0.68
    ୁ
    0.68
    নগর
    0.66
     toaster
    0.66
     vaja
    0.66
    Activations Density 0.043%

    No Known Activations