© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112108
    Prev
    Next
    INDEX
    Explanations

    angular velocity, resolution, momentum

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

    The neuron detects numeric measurement values—especially decimal numbers—most often in technical phrases involving angular parameters.

    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
     “
    -2.31
    to
    -2.14
    逦
    -2.05
    思います
    -1.92
    屺
    -1.84
    胧
    -1.81
    壢
    -1.81
     “,
    -1.80
    Isn
    -1.74
     icônes
    -1.74
    POSITIVE LOGITS
    ated
    2.11
    </h2>
    1.97
     that
    1.85
     versatile
    1.83
    ized
    1.80
    䉴
    1.71
     popularly
    1.71
     of
    1.68
     achievable
    1.66
     this
    1.65
    Activations Density 0.019%

    No Known Activations