© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14829
    Prev
    Next
    INDEX
    Explanations

    code: machine, File, button, nodes

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

    The neuron strongly responds to numeric or quantitative expressions—e.g. digits, counts, time units, and measurement terms.

    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_24_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
    ดัน
    0.71
     jungen
    0.67
    >∞</
    0.67
    Tip
    0.65
     Tip
    0.63
     Symmetry
    0.63
    WILLIAM
    0.62
    ครัว
    0.61
    yle
    0.60
     b
    0.59
    POSITIVE LOGITS
     подар
    0.92
    lices
    0.90
     myocytes
    0.89
    াহিয়া
    0.88
     раза
    0.86
     толькі
    0.86
    ̣t
    0.86
     thoracique
    0.84
     particules
    0.84
     підпри
    0.83
    Activations Density 0.000%

    No Known Activations