© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105336
    Prev
    Next
    INDEX
    Explanations

    units and IU

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

    The neuron flags tokens denoting measurement units (e.g., “units,” “U/ml,” “unit”) often following numerical 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
     bezw
    -2.02
     zwi
    -1.90
     emporio
    -1.80
     vijf
    -1.74
     jaket
    -1.73
    必须要
    -1.70
     heo
    -1.67
     Inſ
    -1.66
    ちょ
    -1.64
     Aeropuerto
    -1.64
    POSITIVE LOGITS
    なので
    1.89
     It
    1.87
    一月
    1.63
     hikes
    1.59
    高端
    1.53
    tización
    1.51
    的呢
    1.51
    探讨
    1.49
     Since
    1.49
    殭
    1.48
    Activations Density 0.034%

    No Known Activations