© 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. 4182
    Prev
    Next
    INDEX
    Explanations

    to + verb

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

    The neuron strongly activates on verbs expressing intent or desire (e.g. want, need, have to, intend).

    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
     by
    1.07
     during
    1.05
     in
    1.03
    m
    0.98
    f
    0.98
    it
    0.97
     fervor
    0.93
    able
    0.93
    ↵
    0.90
     of
    0.88
    POSITIVE LOGITS
     하고
    1.00
    Cadastro
    0.98
     Такой
    0.96
    Particle
    0.95
     그냥
    0.95
    NSLog
    0.94
    MDg
    0.92
    Bokeh
    0.91
     Cái
    0.89
     Моск
    0.88
    Activations Density 0.000%

    No Known Activations