© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64314
    Prev
    Next
    INDEX
    Explanations

    language register and style

    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
     giặt
    -0.79
    افر
    -0.77
    ophysical
    -0.75
     ética
    -0.74
    的眼神
    -0.73
    itari
    -0.72
    cloudf
    -0.72
    istaa
    -0.71
    ultat
    -0.70
    を行いました
    -0.70
    POSITIVE LOGITS
     Standard
    1.88
    Standard
    1.83
     standard
    1.75
    标准
    1.52
    standard
    1.49
     estándar
    1.33
     dialect
    1.32
     STANDARD
    1.28
    標準
    1.27
    STANDARD
    1.20
    Activations Density 0.050%

    No Known Activations