© 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. 15751
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens containing 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
     krzy
    0.80
     servizio
    0.79
     şi
    0.78
     đọc
    0.78
     suelo
    0.75
    iny
    0.74
    ੜ
    0.72
    ൪
    0.71
    क्षेप
    0.71
    zzel
    0.71
    POSITIVE LOGITS
    CO
    0.82
    Two
    0.77
    d
    0.75
    CH
    0.74
    From
    0.74
    Secret
    0.72
    Three
    0.72
     비롯
    0.70
    Ex
    0.69
    Seven
    0.69
    Activations Density 0.052%

    No Known Activations