© 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. 9035
    Prev
    Next
    INDEX
    Explanations

    familiar content

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

    The neuron 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
    ről
    0.95
    beth
    0.78
     leid
    0.77
     nėra
    0.77
    kte
    0.76
     dönüş
    0.73
    deutsch
    0.73
    喽
    0.72
    ू
    0.72
     kon
    0.71
    POSITIVE LOGITS
     Baru
    0.84
     Numpy
    0.76
     Alloys
    0.75
     Energies
    0.73
     wagons
    0.72
     тренер
    0.72
    👖
    0.72
     ALLOYS
    0.69
    ~(
    0.69
     ContentValues
    0.69
    Activations Density 0.000%

    No Known Activations