© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    long history

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specifically fires on numeric tokens—especially floating‐point numbers in the text.

    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
    ار
    1.34
    ak
    1.28
    AT
    1.27
    oarthritis
    1.23
    ្នុង
    1.21
    yong
    1.20
    り
    1.19
    zsche
    1.15
    em
    1.13
    ok
    1.13
    POSITIVE LOGITS
     (>
    1.28
     ago
    1.22
    parseLong
    1.18
     זמן
    1.17
    itud
    1.13
    awaited
    1.13
    以來
    1.11
    ق
    1.07
    ě
    1.06
    以来
    1.04
    Activations Density 0.052%

    No Known Activations