© 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. 10678
    Prev
    Next
    INDEX
    Explanations

    infection and followed by conjunctions

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

    The neuron fires on numeric tokens containing 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
     generalization
    0.94
    VITY
    0.84
    +}
    0.80
     SUSY
    0.79
     Bohr
    0.78
     generalizations
    0.77
     generalized
    0.77
     covariant
    0.77
     synergistic
    0.76
     payback
    0.76
    POSITIVE LOGITS
    ه
    0.98
    ا
    0.76
    י
    0.76
    library
    0.75
    های
    0.74
    uus
    0.73
    ié
    0.73
    و
    0.73
     and
    0.71
    ي
    0.71
    Activations Density 0.001%

    No Known Activations