© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7752
    Prev
    Next
    INDEX
    Explanations

    processes, coverage, targeting

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

    The neuron fires on numeric tokens and quantitative figures (e.g. monetary amounts, thresholds, counts) 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
    stud
    0.74
    Humans
    0.71
    humans
    0.68
    America
    0.68
    various
    0.66
    Sin
    0.66
    Polynomial
    0.65
    岳
    0.64
    Religion
    0.64
    Magn
    0.63
    POSITIVE LOGITS
     nominating
    0.82
     triggering
    0.75
     submissions
    0.73
     inoculum
    0.72
     coverage
    0.71
     nominate
    0.71
     submits
    0.71
     berharap
    0.70
     mobilisation
    0.69
     uploading
    0.68
    Activations Density 0.278%

    No Known Activations