© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63442
    Prev
    Next
    INDEX
    Explanations

    units of measurement

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

    The neuron specializes in detecting numeric measurement values paired with their units (e.g., “cm,” “GHz,” “dB,” “mW,” etc.).

    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
     of
    -2.73
     to
    -1.37
    ='
    -1.18
    ของ
    -1.10
    of
    -1.03
    Number
    -1.03
    num
    -1.02
    AND
    -1.01
    ,'
    -1.01
    说到
    -0.98
    POSITIVE LOGITS
    diseases
    1.27
    uties
    1.15
    ousand
    1.13
     ihan
    1.13
     teori
    1.13
    nthe
    1.13
    Поэтому
    1.12
    achieved
    1.12
    Curios
    1.11
     maksi
    1.10
    Activations Density 0.129%

    No Known Activations