© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9660
    Prev
    Next
    INDEX
    Explanations

    counting bits

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

    The neuron is specialized in spotting numeric tokens—especially integer or floating‐point values used as parameters in technical or problem‐statement 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_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
     algorithmic
    0.69
    ᒡ
    0.63
     algoritmo
    0.63
    étation
    0.61
    льзя
    0.61
     न्यूमेर
    0.60
     деп
    0.58
     intramolecular
    0.58
    python
    0.58
     ورح
    0.58
    POSITIVE LOGITS
     W
    0.64
    𝑛
    0.60
     S
    0.55
     cylinders
    0.52
     एस
    0.51
     hoses
    0.51
    ﾝ
    0.51
     Relating
    0.50
     oil
    0.50
    的能力
    0.49
    Activations Density 0.002%

    No Known Activations