© 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. 78379
    Prev
    Next
    INDEX
    Explanations

    it's high time

    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
    叁
    -0.76
    OutputPath
    -0.75
    kaner
    -0.75
     πάντα
    -0.74
    irc
    -0.74
    रिक
    -0.74
     بز
    -0.73
     elkaar
    -0.73
     پو
    -0.72
    ジュニア
    -0.72
    POSITIVE LOGITS
     high
    4.22
    high
    3.47
    High
    3.13
     High
    2.73
    HIGH
    2.47
    高
    2.41
     HIGH
    2.23
     hög
    1.94
     about
    1.80
     высо
    1.79
    Activations Density 0.031%

    No Known Activations