© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 416
    Prev
    Next
    INDEX
    Explanations

    hotlines and crisis numbers

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

    The neuron detects tokens composed of multi‐digit numbers (e.g. street numbers, phone numbers, and other numeric strings).

    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
    ,
    0.25
    y
    0.22
    :
    0.21
    -
    0.21
    .
    0.20
    7
    0.20
    '
    0.20
     these
    0.19
    ;
    0.19
    9
    0.19
    POSITIVE LOGITS
     अनुप्रयोग
    0.20
     există
    0.19
     RasterModelGrid
    0.19
     município
    0.19
    ﺎ
    0.19
     फक्त
    0.19
     ένας
    0.19
     بابەت
    0.19
    <unused2123>
    0.19
     регі
    0.19
    Activations Density 0.361%

    No Known Activations