© 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. 13333
    Prev
    Next
    INDEX
    Explanations

    The neuron is selectively activating on numeric tokens that include a decimal point (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
     certainement
    0.83
     Instantiate
    0.83
    ׳
    0.82
     effectivement
    0.79
     powodu
    0.79
     elle
    0.77
     seara
    0.77
     %,
    0.77
    ₺
    0.77
    불어
    0.77
    POSITIVE LOGITS
    ش
    0.79
    ContextHeader
    0.75
     получен
    0.66
     slurry
    0.66
    中年
    0.65
     sulfide
    0.64
     attuned
    0.64
    iami
    0.64
    wet
    0.64
     sulphide
    0.64
    Activations Density 0.000%

    No Known Activations