© 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. 3784
    Prev
    Next
    INDEX
    Explanations

    wireless freedom, motion, AI, work

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

    The neuron fires most strongly on longer, multi-syllabic content words (i.e. polysyllabic, less frequent vocabulary).

    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
     僕
    0.89
     поговорим
    0.82
     gobiernos
    0.79
     enemigos
    0.79
    တွေကို
    0.79
     쭉
    0.79
     そんな
    0.77
    ِن
    0.77
    をはじめ
    0.77
    はもちろん
    0.77
    POSITIVE LOGITS
    /
    0.95
     during
    0.76
     within
    0.75
    0.75
     use
    0.73
     give
    0.73
     two
    0.73
     cable
    0.73
     on
    0.73
     using
    0.71
    Activations Density 0.217%

    No Known Activations