© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    compliance legislation

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

    This neuron responds to discourse-linking words and adverbial transitions (e.g. “Rather,” “significantly,” “introduction,” “due to,” “codes”).

    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
    ע
    0.91
    Đ
    0.90
    Esto
    0.89
    Ż
    0.87
    П
    0.86
    Bộ
    0.84
    Buscar
    0.80
    Este
    0.79
    Ş
    0.79
     représent
    0.78
    POSITIVE LOGITS
    らく
    0.76
    रिडोर
    0.76
    boiled
    0.75
     Admittedly
    0.75
     такой
    0.75
     Heuer
    0.73
     smeared
    0.72
     alkaloids
    0.72
     srcset
    0.71
     понятия
    0.71
    Activations Density 0.000%

    No Known Activations