© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60199
    Prev
    Next
    INDEX
    Explanations

    magnetic susceptibility, specific strength, transition temperatures

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

    The neuron flags technical scientific measurement terms—names of physical properties (like susceptibilities, coefficients, strengths, densities, phase‐transition temperatures) and analytical methods (e.g. calorimetry, microcalorimetry).

    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
    跸
    -1.66
    玧
    -1.61
     consegu
    -1.54
    гии
    -1.52
    ꯴
    -1.52
    毟
    -1.52
    град
    -1.45
    érer
    -1.44
    ших
    -1.40
    quoise
    -1.40
    POSITIVE LOGITS
     on
    1.62
     believing
    1.38
    4
    1.38
    鹮
    1.38
    她的
    1.37
     вашей
    1.35
     colour
    1.34
    1.34
    this
    1.34
    ve
    1.33
    Activations Density 0.014%

    No Known Activations