© 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. 107641
    Prev
    Next
    INDEX
    Explanations

    scroll related terms

    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_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
    𝓮
    -0.83
     APART
    -0.78
    erei
    -0.75
     sufficiently
    -0.73
     Cheddar
    -0.73
     Casio
    -0.72
    Người
    -0.71
     довольно
    -0.71
     approved
    -0.71
     organized
    -0.71
    POSITIVE LOGITS
     sco
    0.98
     nele
    0.86
     scroll
    0.85
     Scroll
    0.83
    GOP
    0.78
    Основные
    0.77
     kapak
    0.77
    Yon
    0.77
     telas
    0.77
    klaim
    0.76
    Activations Density 0.012%

    No Known Activations