© 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. 31-GEMMASCOPE-2-RES-16K
    7. 363
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (including floats and other number‐like strings).

    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
     การ
    0.35
    )=\{
    0.31
     プロ
    0.31
     XOR
    0.30
     привіт
    0.30
     hola
    0.30
     leichter
    0.30
     Bienvenidos
    0.30
     हेलो
    0.29
     eure
    0.29
    POSITIVE LOGITS
    further
    0.34
    uncertain
    0.33
    foresaid
    0.32
    pert
    0.31
    <blockquote>
    0.31
    perman
    0.31
    页面存档备份
    0.31
    permitted
    0.31
    promised
    0.31
    pointed
    0.31
    Activations Density 0.244%

    No Known Activations