© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34340
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    The neuron flags domain‐specific “jargon” or technical terms—things like compiler flags and code directives, medical procedure names, and other specialized vocabulary.

    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
     < 
    -1.15
     partagé
    -1.05
    ____________
    -1.02
    estimable
    -1.01
    zemu
    -0.99
    ״
    -0.99
     trovo
    -0.98
     lacs
    -0.97
    ciendo
    -0.97
    continence
    -0.96
    POSITIVE LOGITS
     nagging
    0.91
     TAMBÉM
    0.88
    ｳ
    0.87
    юрпри
    0.87
    衬衫
    0.85
     reinstalling
    0.84
     czerwca
    0.84
    といって
    0.84
     stratég
    0.83
     Heizung
    0.82
    Activations Density 0.184%

    No Known Activations