© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15797
    Prev
    Next
    INDEX
    Explanations

    function arguments

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

    The neuron fires on numeric markers in bibliographic references (e.g., page numbers, ISBNs, volume and issue numbers).

    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
     …..
    0.61
     –
    0.59
     ~\
    0.58
     ……..
    0.54
     tabii
    0.52
    لمات
    0.52
     홀
    0.51
     -
    0.51
    …..
    0.48
    …….
    0.48
    POSITIVE LOGITS
     empe
    0.59
     miserably
    0.57
     nariz
    0.54
    Topbar
    0.54
     સફળ
    0.54
    renal
    0.52
    Flipper
    0.52
    getP
    0.51
     elaborate
    0.51
    BINARY
    0.50
    Activations Density 0.019%

    No Known Activations