© 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. 22-GEMMASCOPE-RES-131K
    7. 72898
    Prev
    Next
    INDEX
    Explanations

    android xml resources

    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
     all
    -1.72
    なぜ
    -1.57
    viève
    -1.35
     ușor
    -1.27
    ppings
    -1.26
    醅
    -1.26
    ÑOS
    -1.23
    調味料
    -1.16
    動物園
    -1.16
    それでも
    -1.15
    POSITIVE LOGITS
    為に
    1.67
    外部链接
    1.47
     DURING
    1.37
    ところです
    1.29
    M
    1.28
    ようです
    1.24
     verschiedener
    1.23
    ようで
    1.20
    during
    1.18
    튿
    1.18
    Activations Density 0.003%

    No Known Activations