© 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. 34-GEMMASCOPE-RES-131K
    7. 107772
    Prev
    Next
    INDEX
    Explanations

    Q: forum or code question

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

    This neuron fires on XML/HTML structural markup (angle-bracket tags and their indentation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Trichloroethane
    -0.86
     måde
    -0.85
    tyg
    -0.83
    šení
    -0.82
     LoggerFactory
    -0.81
    chaise
    -0.80
    ₿
    -0.80
    FORMANCE
    -0.80
     varit
    -0.79
    rungsseite
    -0.78
    POSITIVE LOGITS
     cuff
    0.88
    gelegt
    0.78
    atized
    0.78
    ële
    0.77
    camin
    0.77
    AGES
    0.77
     języka
    0.77
     ova
    0.76
     dn
    0.75
    denken
    0.73
    Activations Density 0.011%

    No Known Activations