© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10634
    Prev
    Next
    INDEX
    Explanations

    taking bits or letters

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

    The neuron activates on numeric values (especially multi‐digit numbers and decimals).

    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
    ності
    0.84
    ما
    0.83
    ванням
    0.83
     红
    0.78
    红
    0.77
    三星
    0.77
     वाटते
    0.77
    ع
    0.77
    nın
    0.76
    ალ
    0.75
    POSITIVE LOGITS
    et
    0.97
     betek
    0.77
     Haga
    0.76
    but
    0.76
    yet
    0.75
     weten
    0.75
    oi
    0.72
     mengingat
    0.71
     vekt
    0.71
     meses
    0.71
    Activations Density 0.000%

    No Known Activations