© 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. 2380
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone decimal‐point numbers (floating‐point numerals).

    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
     Theological
    0.64
    环
    0.59
    bmod
    0.58
     Salv
    0.56
     Zaman
    0.55
    Methylsulfanyl
    0.55
     Gesicht
    0.55
    clave
    0.54
    Saver
    0.54
    setcounter
    0.53
    POSITIVE LOGITS
    <h2>
    0.84
    <h3>
    0.68
    NOTE
    0.57
    <
    0.57
    жуть
    0.57
     déterminé
    0.57
     consultant
    0.56
     informée
    0.56
     <
    0.55
    ดู
    0.55
    Activations Density 0.001%

    No Known Activations