© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1179
    Prev
    Next
    INDEX
    Explanations

    he or she speaks

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

    The neuron specifically fires on numeric tokens with decimal points (floating-point 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_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
    plements
    0.60
     ergonomic
    0.54
     youll
    0.54
    ↵↵
    0.50
    ↵↵↵
    0.50
     optionally
    0.50
     accessor
    0.50
     комплект
    0.50
    <unused99>
    0.50
     youre
    0.50
    POSITIVE LOGITS
    他說
    0.84
     เขา
    0.80
    他说
    0.78
    他在
    0.76
    彼は
    0.76
     그는
    0.73
     "[
    0.72
    "[
    0.70
     “[
    0.69
    ibid
    0.68
    Activations Density 0.004%

    No Known Activations