© 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. 34-GEMMASCOPE-RES-131K
    4. 102691
    Prev
    Next
    INDEX
    Explanations

    xml version

    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
     iu
    -0.79
     java
    -0.75
     tô
    -0.73
    canada
    -0.71
     tilbake
    -0.70
    StackTrace
    -0.69
     Weiss
    -0.68
    ляются
    -0.68
    Weiss
    -0.68
    巨
    -0.67
    POSITIVE LOGITS
    ileo
    0.82
    開啟
    0.77
    istaa
    0.76
    neq
    0.72
     Inferior
    0.71
     démar
    0.71
     Versace
    0.71
     Karak
    0.70
    デザート
    0.70
    开启
    0.70
    Activations Density 0.055%

    No Known Activations