© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1139
    Prev
    Next
    INDEX
    Explanations

    code separators and keywords

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

    The neuron strongly activates on numeric tokens (especially decimal numbers) such as those used in citations, specifications, or statistical 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_24_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
    ers
    0.46
    =
    0.43
     факторов
    0.41
     cevap
    0.40
     bzw
    0.39
    gäng
    0.39
    GBuf
    0.38
     বাড়
    0.37
     substituents
    0.37
     venons
    0.37
    POSITIVE LOGITS
    של
    0.42
    ोला
    0.40
    stdin
    0.39
    ِل
    0.38
    আ
    0.38
    URDAY
    0.38
    isième
    0.37
     الأول
    0.37
     Lite
    0.37
    এর
    0.37
    Activations Density 0.056%

    No Known Activations