© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119491
    Prev
    Next
    INDEX
    Explanations

    organizations and brands

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

    This neuron detects the ampersand character (“&”) in text.

    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
     but
    -2.09
    .
    -1.92
     impeccable
    -1.86
     When
    -1.82
     Shortly
    -1.79
    because
    -1.73
     poignant
    -1.71
     Often
    -1.70
     Using
    -1.69
     impressive
    -1.69
    POSITIVE LOGITS
     dezelve
    2.06
     tranſ
    2.05
     Dinas
    1.88
     zoude
    1.84
    跟你
    1.82
    稞
    1.75
     😁
    1.75
     uyt
    1.73
     flink
    1.73
    -*
    1.72
    Activations Density 0.021%

    No Known Activations