© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    tracking, providing, information

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

    The neuron detects strong personal‐modality verbs that express obligation, desire, or future intent (e.g. “need,” “will,” “praying”).

    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
     xạ
    0.95
    鴟
    0.82
     পিঁপড়ার
    0.78
    ֒
    0.77
    unprocessable
    0.76
    гти
    0.75
     بل
    0.75
    ھ
    0.75
    चुअल
    0.74
    激素
    0.74
    POSITIVE LOGITS
    ten
    0.98
    AN
    0.84
     lancer
    0.82
     values
    0.77
     snapped
    0.76
    n
    0.75
     snap
    0.74
    TERS
    0.73
    VIOUS
    0.73
     dollar
    0.72
    Activations Density 0.014%

    No Known Activations