© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    numbers and list structures

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

    The main thing this neuron does is detect numeric tokens and coded number sequences 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_31_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
     bilayer
    0.61
     methane
    0.59
     sinusoidal
    0.59
     Nitrogen
    0.59
    钾
    0.59
     viscoelastic
    0.58
     alkalinity
    0.58
     nitrogen
    0.57
    ãy
    0.57
    ỉ
    0.57
    POSITIVE LOGITS
     wilfully
    0.61
     debuting
    0.59
     psic
    0.57
     হতেই
    0.57
    bigcup
    0.56
     मोठ
    0.56
     immort
    0.55
    arranged
    0.55
     debuts
    0.55
     cub
    0.54
    Activations Density 0.000%

    No Known Activations