© 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. 40841
    Prev
    Next
    INDEX
    Explanations

    timing and precision

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

    The neuron is primarily activated by occurrences of the word “timing.”

    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
     “
    -2.81
    “
    -2.56
     ”
    -2.53
     (“
    -2.53
     
    -2.50
    ’
    -2.45
     
    -2.39
     “(
    -2.33
     –
    -2.31
     —
    -2.25
    POSITIVE LOGITS
    鋨
    3.09
    ၟ
    2.80
    釓
    2.58
    銪
    2.53
     entreprise
    2.53
    鈰
    2.45
    衚
    2.44
    alties
    2.41
     休闲
    2.38
    擷
    2.38
    Activations Density 0.003%

    No Known Activations