© 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. 2938
    Prev
    Next
    INDEX
    Explanations

    restaurant and eating places

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

    The neuron primarily detects numeric tokens—especially floating‐point numbers and other digits.

    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
    bedroom
    0.78
    ᆷ
    0.78
    esterday
    0.73
    feet
    0.73
    rover
    0.70
    మై
    0.69
    𝔞
    0.69
    NP
    0.68
    billion
    0.68
    academic
    0.67
    POSITIVE LOGITS
     gastronom
    0.99
    レストラン
    0.97
     gastronomy
    0.91
     gastronomic
    0.88
     ресторан
    0.86
     también
    0.85
     restaurant
    0.84
     ristor
    0.84
     також
    0.83
     gastron
    0.82
    Activations Density 0.002%

    No Known Activations