© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to 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_31_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
    [
    0.29
     localhost
    0.28
     Geheim
    0.28
    Chinese
    0.28
    Homo
    0.27
    ИК
    0.27
     Chinese
    0.26
    [*
    0.26
    פקי
    0.26
    </h2>
    0.26
    POSITIVE LOGITS
    ureen
    0.35
     Amanda
    0.35
    㤓
    0.33
    捙
    0.33
     Megan
    0.33
    秏
    0.32
     بب
    0.32
    蚛
    0.32
    婹
    0.31
    йда
    0.31
    Activations Density 0.284%

    No Known Activations