© 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. 3905
    Prev
    Next
    INDEX
    Explanations

    for

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

    The neuron detects sequences of uppercase tokens with accented characters typical of Spanish or Portuguese text.

    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
    Ét
    0.59
    Votre
    0.54
    ពួកគេ
    0.53
     Джон
    0.52
    Você
    0.52
    ngày
    0.52
    ឮ
    0.52
    Datei
    0.50
    គាត់
    0.50
    ジョン
    0.50
    POSITIVE LOGITS
     fertilizers
    0.56
    .
    0.54
    ,
    0.52
     monoton
    0.49
     ionizing
    0.48
     monomer
    0.48
     gangsters
    0.47
     mechanized
    0.47
     armored
    0.47
     piu
    0.47
    Activations Density 0.176%

    No Known Activations