© 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. 90822
    Prev
    Next
    INDEX
    Explanations

    that if since

    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
    牠
    -0.98
    ontroller
    -0.96
     tohoto
    -0.93
    subsid
    -0.93
    multicolumn
    -0.92
    のではなく
    -0.92
     Mathis
    -0.91
    irited
    -0.91
    用了
    -0.90
    ANNELS
    -0.90
    POSITIVE LOGITS
     every
    2.23
     any
    2.16
     for
    1.92
     if
    1.86
     each
    1.72
    every
    1.57
     there
    1.54
    每个
    1.48
    Every
    1.43
    any
    1.42
    Activations Density 0.055%

    No Known Activations