© 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. 10035
    Prev
    Next
    INDEX
    Explanations

    Keywords, Explanation, Bug, Reason, wiki, doc

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

    The neuron strongly activates on the numeric document‐level metrics (e.g. file sizes, word counts, lengths) that appear after each 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
    észet
    0.58
    frist
    0.57
    uese
    0.57
    ܵ
    0.57
     dear
    0.55
    seud
    0.55
    oves
    0.54
    atud
    0.54
    屣
    0.53
    atio
    0.52
    POSITIVE LOGITS
     cDNA
    0.66
     analogs
    0.61
     Año
    0.61
     Bedürfn
    0.57
     Bering
    0.57
    ply
    0.57
     memes
    0.57
    рано
    0.57
     VLAN
    0.57
     başlayan
    0.57
    Activations Density 0.000%

    No Known Activations