© 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. 110669
    Prev
    Next
    INDEX
    Explanations

    class, pattern, isa, bool

    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
    asyarakat
    -0.88
     palladium
    -0.83
     شود
    -0.81
     المغرب
    -0.80
    Ϊ
    -0.79
    hooting
    -0.77
     ate
    -0.77
     knot
    -0.73
     pollin
    -0.73
    zestaw
    -0.73
    POSITIVE LOGITS
     шанс
    0.85
    ʕ
    0.82
     DESCRIPTION
    0.80
    گوشی
    0.79
    ochemistry
    0.76
    ITATION
    0.75
    ALIAS
    0.73
     participe
    0.73
     актуаль
    0.73
     проведе
    0.72
    Activations Density 0.071%

    No Known Activations