© 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. 22-GEMMASCOPE-RES-131K
    7. 35595
    Prev
    Next
    INDEX
    Explanations

    comparisons of measurements

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

    The neuron activates on technical terms denoting scientific measurements or physical quantities (e.g., radiation, wavelengths, emission, particulate diameters, temperatures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     knew
    -1.09
     one
    -1.08
     would
    -1.06
     it
    -1.01
     might
    -0.99
     and
    -0.98
     volumen
    -0.98
    豋
    -0.97
    matig
    -0.97
    ＾＾
    -0.96
    POSITIVE LOGITS
     between
    2.14
     beyond
    1.59
     above
    1.45
     below
    1.27
     greater
    1.21
     up
    1.20
     przede
    1.20
     exceeding
    1.17
     >=
    1.16
     predominantly
    1.14
    Activations Density 0.052%

    No Known Activations