© 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. 10355
    Prev
    Next
    INDEX
    Explanations

    computation and physics terminology

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

    This neuron detects capitalized technical terms or labels (e.g. section names or API/feature identifiers).

    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
     or
    -1.84
     should
    -1.35
     will
    -1.34
     
    -1.27
     hizo
    -1.23
     this
    -1.20
     cuando
    -1.18
     olması
    -1.18
     olacaktır
    -1.16
     siempre
    -1.15
    POSITIVE LOGITS
     humide
    1.29
    cessite
    1.27
    continence
    1.27
     REGULATION
    1.23
    otropy
    1.22
     EMERGENCY
    1.22
    鲥
    1.20
     vantagem
    1.20
    tdessen
    1.19
     verschiedene
    1.18
    Activations Density 0.002%

    No Known Activations