© 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. 9786
    Prev
    Next
    INDEX
    Explanations

    product units

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

    The neuron specializes in picking out tokens that contain digits or numeric identifiers (e.g., years, file numbers, URLs with numbers).

    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
    ﺅ
    0.90
     Jolla
    0.90
     Bcl
    0.88
    Для
    0.84
    d
    0.83
     Вы
    0.82
    ｋ
    0.82
    re
    0.82
     Dafür
    0.81
     Detalles
    0.80
    POSITIVE LOGITS
     arriv
    0.76
     dirig
    0.74
     arrivé
    0.64
     qualific
    0.64
    тна
    0.64
     arbor
    0.64
     muni
    0.63
     avenue
    0.63
     vòng
    0.63
     traf
    0.62
    Activations Density 0.000%

    No Known Activations