© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numeric tokens and especially floating-point or large numeric values.

    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
    ש
    0.34
    錢
    0.31
    主要是
    0.30
    立马
    0.29
    这也
    0.29
     হয়ত
    0.28
    或者是
    0.28
     педагоги
    0.28
     ибо
    0.28
    ਟ
    0.27
    POSITIVE LOGITS
     Richards
    0.33
     Rodgers
    0.29
     എന്നിവ
    0.29
     नामक
    0.28
     (!)
    0.28
     फैन्स
    0.28
     Lance
    0.27
     Randy
    0.26
     Matthews
    0.26
     awoke
    0.26
    Activations Density 4.953%

    No Known Activations