© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    divide by coefficient

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

    The neuron strongly activates on isolated decimal numbers (floating-point values) embedded in the 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
    singleton
    0.61
    pell
    0.59
    requireNonNull
    0.59
    여기
    0.58
    Issuer
    0.58
    韶
    0.58
    这场
    0.57
    buy
    0.57
    γκα
    0.56
    伶
    0.55
    POSITIVE LOGITS
     Frequently
    0.63
     FAQs
    0.59
     twenty
    0.58
     twelve
    0.58
     WEBSITE
    0.58
     Scientists
    0.58
     Resume
    0.58
     rés
    0.57
     RES
    0.57
     Practically
    0.57
    Activations Density 0.000%

    No Known Activations