© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    This neuron spikes on unusually rare or distinctive tokens (e.g. low‐frequency words and proper names).

    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
    נ
    0.76
    નગર
    0.73
    ുള്ള
    0.73
    ösung
    0.71
    aminan
    0.70
    할
    0.70
    ieder
    0.68
    ן
    0.67
    uerpo
    0.66
    თვის
    0.65
    POSITIVE LOGITS
    Oval
    0.99
     Horseshoe
    0.87
     Thanos
    0.86
    One
    0.82
     Kyushu
    0.81
     Mitsubishi
    0.79
     Rothschild
    0.78
    มาจาก
    0.78
    How
    0.77
     Two
    0.77
    Activations Density 0.000%

    No Known Activations