© 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. 10-GEMMASCOPE-RES-131K
    7. 43975
    Prev
    Next
    INDEX
    Explanations

    measurement units

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

    The neuron detects numerical measurements—especially decimal or multi‐digit numbers paired with units or metrics.

    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
     September
    -1.81
     December
    -1.65
     from
    -1.65
     November
    -1.52
     June
    -1.51
     January
    -1.48
     October
    -1.47
    Although
    -1.45
     August
    -1.43
     with
    -1.40
    POSITIVE LOGITS
    ⢱
    1.70
     этого
    1.59
    ABETH
    1.44
     Ucraina
    1.39
     når
    1.30
     Celebrations
    1.30
     Kampung
    1.29
     tecnología
    1.27
     てき
    1.27
     Teks
    1.27
    Activations Density 0.059%

    No Known Activations