© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    after pauses or String

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

    This neuron fires on numerical tokens representing decimal values (numbers containing a period).

    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
     Однако
    1.01
     न्यूमेर
    0.88
     einzigen
    0.88
     Только
    0.86
    :'],
    0.86
    emptyDict
    0.86
     Дэ
    0.84
     высота
    0.82
     Еще
    0.81
     однако
    0.81
    POSITIVE LOGITS
    0
    0.89
    I
    0.88
    ↵
    0.70
     I
    0.69
    lk
    0.68
    BA
    0.67
    Z
    0.66
    <0x0D>
    0.66
    maid
    0.66
    SC
    0.65
    Activations Density 0.000%

    No Known Activations