© 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. 9883
    Prev
    Next
    INDEX
    Explanations

    output format

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

    The neuron fires on subword tokens containing digits or punctuation (e.g. decimal numbers, percentages, hyphen-ated fragments, and quote‐marks) rather than ordinary words.

    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
     mh
    0.60
     EK
    0.58
    눠
    0.57
     Bourgoin
    0.56
     hyperplane
    0.55
     общество
    0.54
    乑
    0.54
     (^
    0.53
     Oj
    0.52
     Dy
    0.52
    POSITIVE LOGITS
    wolves
    0.60
    даго
    0.60
    喜爱
    0.60
    supports
    0.57
    のために
    0.56
     বাত
    0.55
    GGA
    0.55
    REND
    0.55
    IsOpen
    0.55
    živ
    0.55
    Activations Density 0.000%

    No Known Activations