© 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. 10353
    Prev
    Next
    INDEX
    Explanations

    listing items or sections

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

    The neuron is highly sensitive to numeric references and enumerations (e.g. step, figure, claim, episode, or version numbers) in the 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
     whatnot
    0.54
     पारिवार
    0.53
     frameworks
    0.53
     pudi
    0.53
    <unused105>
    0.52
    jähr
    0.52
    সম্প
    0.51
    ம்த
    0.51
    "><?=$
    0.51
    ിയ്
    0.51
    POSITIVE LOGITS
    第
    2.14
     第
    1.89
     Chapter
    1.77
    Chapter
    1.61
    第五
    1.60
     Section
    1.56
    第八
    1.49
    第七
    1.47
    第六
    1.42
     Episode
    1.41
    Activations Density 0.933%

    No Known Activations