© 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. 2865
    Prev
    Next
    INDEX
    Explanations

    quantities and monetary estimates

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

    The neuron responds to numeric measurements or quantities—especially numbers with decimal points.

    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
    ("
    0.54
    _
    0.53
    res
    0.52
    ises
    0.52
    the
    0.50
    ization
    0.50
    ização
    0.50
    re
    0.49
    isieren
    0.48
    '
    0.48
    POSITIVE LOGITS
     ~$
    0.75
     १५
    0.75
     cientos
    0.74
     decenas
    0.73
    十几
    0.72
     ۱۵
    0.71
     jährlich
    0.70
     ₹
    0.69
     crore
    0.69
    几十
    0.68
    Activations Density 0.126%

    No Known Activations