© 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. 1511
    Prev
    Next
    INDEX
    Explanations

    K, Inference, AVC, Budget, Laser

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

    The neuron fires on standalone numeric tokens (digits or decimal numbers), e.g. years or measured values.

    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
    modules
    0.91
    ../../../
    0.88
    n
    0.82
    ateurs
    0.82
    d
    0.80
    énergie
    0.79
    mà
    0.77
    convers
    0.76
     Gatt
    0.75
    m
    0.75
    POSITIVE LOGITS
    =
    0.84
    )
    0.81
     fared
    0.77
     perpetrated
    0.76
     fulfills
    0.75
     equilibrated
    0.75
     enterprising
    0.74
     prow
    0.73
     superbly
    0.73
     Jody
    0.73
    Activations Density 0.001%

    No Known Activations