© 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. 22-GEMMASCOPE-RES-131K
    7. 14019
    Prev
    Next
    INDEX
    Explanations

    media content types

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

    The neuron flags the words used as section or category headers in code or configuration files.

    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
    izace
    -0.98
    菜單
    -0.96
     kapit
    -0.92
    需要
    -0.91
     miliar
    -0.89
    ઉ
    -0.88
    nalité
    -0.88
     DIMENSIONS
    -0.87
     memerlukan
    -0.86
     Rússia
    -0.86
    POSITIVE LOGITS
    Dettagli
    1.02
    Preparazione
    1.00
    ITÀ
    0.99
    otheek
    0.96
    ύ
    0.93
    haël
    0.93
    Calendario
    0.92
     viņ
    0.91
    ścic
    0.91
     año
    0.89
    Activations Density 0.008%

    No Known Activations