© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric expressions containing decimal points (e.g., measurements or values with decimals).

    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
    ه
    0.87
    iť
    0.86
     gesamte
    0.82
    ać
    0.82
    ชุด
    0.80
    ی
    0.80
     ganze
    0.80
     chords
    0.79
     Iqbal
    0.79
    iado
    0.77
    POSITIVE LOGITS
    ри
    1.19
    ొప్ప
    0.93
     sidelines
    0.81
    坡
    0.81
    affichage
    0.80
    marginY
    0.80
    óf
    0.80
     horseback
    0.80
    ९
    0.80
     behalf
    0.79
    Activations Density 0.171%

    No Known Activations