© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10820
    Prev
    Next
    INDEX
    Explanations

    days and events

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

    The neuron strongly activates on numeric literals with decimal points (i.e. 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
    P
    0.89
    R
    0.84
    E
    0.83
     нашей
    0.81
    เห็น
    0.81
     vezet
    0.81
    U
    0.80
    C
    0.78
    ствен
    0.76
    ный
    0.75
    POSITIVE LOGITS
     pétales
    0.93
     États
    0.87
     Concepción
    0.83
     Ephesians
    0.81
     Episcopal
    0.76
     INC
    0.75
     passions
    0.75
    दाबाद
    0.75
     légende
    0.75
    illä
    0.74
    Activations Density 0.001%

    No Known Activations