© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11951
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric tokens (including digits and decimal‐formatted 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
     Beaches
    0.58
    Farland
    0.54
     চলচ্চিত্র
    0.53
    ︱
    0.52
     Cosmetics
    0.51
     Hillsborough
    0.51
    ,’’
    0.51
    
    0.50
    <unused2159>
    0.49
     Woman
    0.49
    POSITIVE LOGITS
     dunno
    0.71
     bzw
    0.67
     shitty
    0.63
     ~$
    0.62
     IMHO
    0.61
    🥜
    0.61
     (=
    0.61
     ppl
    0.61
    /
    0.61
     (~
    0.59
    Activations Density 0.154%

    No Known Activations