© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13352
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently activates on tokens that are floating‐point numbers (i.e. numeric strings containing a decimal point).

    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
     Wordpress
    0.90
    Istituto
    0.84
    パナソニック
    0.82
    は
    0.82
    ş
    0.81
    wordpress
    0.80
    ioid
    0.79
    us
    0.78
    看板
    0.78
     বলতে
    0.77
    POSITIVE LOGITS
     strengthens
    0.67
     intensification
    0.66
     ecology
    0.64
     |_{
    0.63
     nối
    0.63
    山上
    0.63
    غي
    0.63
     survives
    0.62
    িয়ার
    0.62
     eternal
    0.62
    Activations Density 0.000%

    No Known Activations