© 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. 45419
    Prev
    Next
    INDEX
    Explanations

    questions involving specific topics

    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
     Reſ
    -1.07
    なんだか
    -1.02
     VOOR
    -0.97
    jusqu
    -0.94
    を持っている
    -0.93
    particularly
    -0.92
     dédi
    -0.92
     Gouver
    -0.91
     cív
    -0.90
    either
    -0.90
    POSITIVE LOGITS
     Giving
    1.12
     sebe
    0.96
     Even
    0.91
    UT
    0.91
     obce
    0.88
     />,
    0.87
    ində
    0.87
     covid
    0.87
     if
    0.86
     ()
    
    0.86
    Activations Density 0.005%

    No Known Activations