© 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. 22-GEMMASCOPE-RES-131K
    7. 28640
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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
    也被
    -0.90
    ugio
    -0.88
     комплекс
    -0.86
     definir
    -0.84
    —
    -0.83
    борка
    -0.82
    Keynote
    -0.82
     останов
    -0.81
     Trabajo
    -0.81
     bicara
    -0.80
    POSITIVE LOGITS
    kyou
    0.95
    ♭
    0.94
    ſion
    0.93
    ſi
    0.93
    Bibliografie
    0.93
     anunciar
    0.92
    ヮ
    0.91
    
    0.90
     competitivos
    0.90
    irect
    0.89
    Activations Density 0.024%

    No Known Activations