© 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. 71834
    Prev
    Next
    INDEX
    Explanations

    timing periods or durations

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

    The neuron fires on numeric data tokens—especially numbers with digits and decimal points—marking measurements, statistics, or other numeric values.

    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
    when
    -1.71
    i
    -1.65
    what
    -1.63
    iedenis
    -1.58
     $
    -1.58
    があります
    -1.56
    ORETICAL
    -1.56
     }
    -1.56
    中心的
    -1.52
     beeinflussen
    -1.52
    POSITIVE LOGITS
    羮
    2.02
    ⩤
    2.02
    Ꮞ
    1.99
    '
    1.91
    byshire
    1.89
     Tengo
    1.77
    нас
    1.71
    Its
    1.70
     Atención
    1.70
    The
    1.69
    Activations Density 0.015%

    No Known Activations