© 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. 39130
    Prev
    Next
    INDEX
    Explanations

    HTML structure and content

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

    This neuron detects language‐code or locale metadata declarations (e.g. XML/html lang attributes and Content-Language/Coding region entries).

    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
     for
    -2.28
     by
    -1.93
     also
    -1.77
     their
    -1.63
     before
    -1.61
     in
    -1.57
     from
    -1.48
     When
    -1.42
     it
    -1.42
     when
    -1.41
    POSITIVE LOGITS
    扨
    1.84
    without
    1.73
    ఝ
    1.66
    despite
    1.52
     elevada
    1.52
     abbiamo
    1.48
    都想
    1.46
    大概是
    1.45
     mejoras
    1.45
     crescimento
    1.45
    Activations Density 0.000%

    No Known Activations