© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82871
    Prev
    Next
    INDEX
    Explanations

    thickness measurements

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

    The neuron is looking for numeric and measurement expressions—tokens containing digits, ranges, units (e.g. “4-6 mm,” “62”), or other number-related substrings.

    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
    Hundreds
    -0.78
     Monarch
    -0.76
     hundreds
    -0.75
    aney
    -0.75
    кол
    -0.72
    血压
    -0.72
    سی
    -0.72
    oost
    -0.71
     г
    -0.71
     rin
    -0.70
    POSITIVE LOGITS
    Вес
    0.82
     zwölf
    0.81
    fektions
    0.80
     zehn
    0.79
     trum
    0.77
    Solved
    0.77
    conocimiento
    0.76
    crumb
    0.76
    飛び
    0.75
     Appropri
    0.75
    Activations Density 0.041%

    No Known Activations