© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15027
    Prev
    Next
    INDEX
    Explanations

    facial recognition system

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

    The main thing this neuron does is pick out mid-frequency content words (common nouns and verbs) across diverse contexts.

    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
     offrire
    0.91
    tı
    0.90
     aprire
    0.84
     intentar
    0.83
    什么
    0.82
     ماں
    0.80
    狮
    0.80
     obrá
    0.80
    американ
    0.77
    鳟
    0.77
    POSITIVE LOGITS
    over
    0.96
    ree
    0.96
    arg
    0.83
    off
    0.82
    by
    0.81
    ING
    0.81
    ru
    0.80
    imer
    0.80
    hent
    0.80
    ate
    0.80
    Activations Density 0.003%

    No Known Activations