© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39709
    Prev
    Next
    INDEX
    Explanations

    approximating quantities or time

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

    The neuron activates on numeric expressions (e.g. measurements, counts, ages, dates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这般
    -1.63
    讽
    -1.59
    ㍑
    -1.58
     medidor
    -1.55
    狆
    -1.52
     Diputados
    -1.50
     ..............
    -1.50
     haremos
    -1.49
    ᾖ
    -1.48
    愤怒
    -1.48
    POSITIVE LOGITS
    ',
    2.16
    ",
    1.85
    »,
    1.84
    :'
    1.78
     '
    1.67
    ("
    1.60
    wiąz
    1.58
     meinem
    1.58
    ('
    1.55
    (),
    1.55
    Activations Density 0.015%

    No Known Activations