© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40567
    Prev
    Next
    INDEX
    Explanations

    be used in questions

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

    The neuron chiefly activates on numeric tokens and numeric expressions (e.g. integers, decimals, percentages).

    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
    tığı
    -1.77
     tunik
    -1.67
     kleid
    -1.53
     spesifik
    -1.51
    ейчас
    -1.47
     torba
    -1.45
     ferie
    -1.43
    ఉ
    -1.42
    tapete
    -1.42
    nější
    -1.42
    POSITIVE LOGITS
    We
    1.84
    If
    1.73
     "
    1.56
     Also
    1.52
     be
    1.50
    l
    1.49
    to
    1.48
    b
    1.45
    u
    1.45
     Perhaps
    1.45
    Activations Density 0.020%

    No Known Activations