© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12482
    Prev
    Next
    INDEX
    Explanations

    HTML head tags

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     détaillée
    -0.93
     помню
    -0.91
    Ital
    -0.86
    進去
    -0.85
    Melody
    -0.85
     descans
    -0.85
     oyuncak
    -0.83
    頷
    -0.82
    够了
    -0.82
     ebenfalls
    -0.81
    POSITIVE LOGITS
     ‘
    0.96
    Þ
    0.93
    !
    0.90
    þ
    0.89
    namespace
    0.87
     reforma
    0.87
    Ă
    0.86
     ребёнка
    0.85
     tè
    0.84
     海报
    0.83
    Activations Density 0.038%

    No Known Activations