© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10653
    Prev
    Next
    INDEX
    Explanations

    related to other concepts

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

    The neuron detects words that express required or habitual actions, like “regularly,” “frequently,” “required,” and “occasionally.”

    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
    ↵
    0.91
    ো
    0.77
    ાં
    0.75
     रस्त
    0.75
     various
    0.74
     the
    0.71
     permukaan
    0.71
     Fusarium
    0.71
     comes
    0.69
     Gao
    0.68
    POSITIVE LOGITS
    ﻘ
    0.85
    চিৎ
    0.84
    ным
    0.73
    লাষ
    0.72
    ﻗ
    0.72
     जीतने
    0.71
     gebra
    0.71
    ﺛ
    0.71
    চ্ছুক
    0.70
     приступи
    0.70
    Activations Density 0.001%

    No Known Activations