© 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. 86104
    Prev
    Next
    INDEX
    Explanations

    Wai Suk, Battlio, Skippy

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

    This neuron responds to capitalized names, acronyms, or identifier-style tokens (i.e. proper nouns, all-caps abbreviations, or camel-case/code 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
    伟大的
    -2.80
    .”
    -2.80
    ről
    -2.69
    汌
    -2.58
    
    -2.44
    _{
    -2.36
    缈
    -2.30
    ,’
    -2.28
     enamorado
    -2.28
     liegenden
    -2.25
    POSITIVE LOGITS
    *
    3.44
    
    2.73
    "
    2.66
     наше
    2.55
    「
    2.50
     =
    2.47
     fashioned
    2.34
    摀
    2.31
     нашу
    2.28
    er
    2.27
    Activations Density 0.002%

    No Known Activations