© 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. 838
    Prev
    Next
    INDEX
    Explanations

    consists of / encompasses

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

    The neuron fires on numerical tokens—particularly decimal numbers with a dot.

    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
    其
    0.60
     ہوئے۔
    0.55
    ען
    0.54
    Ở
    0.54
     তাতে
    0.53
    在這
    0.52
     IHDA
    0.51
    âni
    0.51
    ЕН
    0.50
     اللّه
    0.50
    POSITIVE LOGITS
     எல்ல
    0.71
     comporte
    0.69
     semua
    0.64
    penas
    0.61
    いです
    0.61
     enthalten
    0.59
    cailles
    0.59
     tất
    0.59
    ु
    0.59
     consists
    0.59
    Activations Density 0.046%

    No Known Activations