© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    directly proportional, split fire, double free

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

    The neuron is triggered by four-digit numeric tokens (often with decimal fractions), i.e. floating-point numbers with four-digit integer parts.

    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
     prisión
    0.52
    োয়া
    0.51
    クリア
    0.50
     중국
    0.49
     испол
    0.49
    ওয়ার্ড
    0.49
    優
    0.49
    潑
    0.49
     SCHEDULE
    0.48
    セ
    0.48
    POSITIVE LOGITS
     Nasr
    0.67
     cosine
    0.63
    ysc
    0.57
    opro
    0.57
    uffin
    0.56
    砀
    0.55
    auz
    0.55
    ्याज
    0.54
     Nes
    0.54
    ahit
    0.54
    Activations Density 0.000%

    No Known Activations