© 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. 13110
    Prev
    Next
    INDEX
    Explanations

    want to only

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

    The neuron selectively fires on numeric tokens—digits and decimal‐formatted numbers—in the text.

    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
     perteneciente
    0.91
    ین
    0.69
    .`
    0.69
    ↞
    0.68
    !!
    0.66
    Questa
    0.66
    !`
    0.66
    ‎
    0.65
    .[
    0.64
    ​.
    0.64
    POSITIVE LOGITS
    ほとんど
    1.04
     možete
    0.93
     కంటే
    0.92
    よりも
    0.91
    难以
    0.91
     거의
    0.89
     merely
    0.89
    只需
    0.88
    幾乎
    0.88
     less
    0.88
    Activations Density 1.618%

    No Known Activations