© 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. 11522
    Prev
    Next
    INDEX
    Explanations

    PRIMARY KEY

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

    The neuron strongly activates on numeric tokens—especially decimal numbers (e.g. volumes, page or article identifiers) as found in academic citations.

    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
    l
    0.80
    逪
    0.79
     incumpl
    0.77
    zov
    0.74
     supprimer
    0.72
     самая
    0.71
     záz
    0.70
     pessoas
    0.69
     sociais
    0.69
    hv
    0.69
    POSITIVE LOGITS
    Tx
    0.70
    大气
    0.66
     उगा
    0.66
     drilled
    0.65
    linearity
    0.65
     dusky
    0.65
    ކ
    0.65
     thrust
    0.64
    fragen
    0.64
    önig
    0.64
    Activations Density 0.001%

    No Known Activations