© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3008
    Prev
    Next
    INDEX
    Explanations

    numbers and random values

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

    The neuron is primarily triggered by numeric tokens that include decimal points (i.e. floating‐point numbers).

    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
    -
    0.75
     
    0.73
    iances
    0.69
     which
    0.68
    sters
    0.67
    '
    0.67
     the
    0.66
    reci
    0.66
    lope
    0.66
     SI
    0.66
    POSITIVE LOGITS
    Ş
    1.00
     extrémités
    0.91
    Bola
    0.91
     ámbitos
    0.91
     colores
    0.86
     लड़का
    0.86
    eş
    0.86
    appartement
    0.86
     appartement
    0.85
    țele
    0.83
    Activations Density 0.000%

    No Known Activations