© 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. 34-GEMMASCOPE-RES-131K
    7. 57465
    Prev
    Next
    INDEX
    Explanations

    ml or cc measurements

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

    The neuron detects quantitative measurement tokens—numbers and unit terms (e.g. “oxygen,” “micrograms,” “ml”)—in scientific text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Meters
    -0.77
    gggg
    -0.73
    Gilla
    -0.73
    vention
    -0.71
     einverstanden
    -0.70
    重量
    -0.68
    mass
    -0.67
    ТЕЛЬ
    -0.66
     Trabal
    -0.66
    moo
    -0.65
    POSITIVE LOGITS
     ml
    2.63
    ml
    2.53
     mL
    2.22
    mL
    2.17
     мл
    1.63
    ML
    1.59
     ML
    1.54
     volume
    1.52
     Ml
    1.47
    cc
    1.43
    Activations Density 0.075%

    No Known Activations