© 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. 10-GEMMASCOPE-RES-131K
    7. 85584
    Prev
    Next
    INDEX
    Explanations

    custom C attributes

    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_10/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
     because
    -2.13
     with
    -2.02
     after
    -1.97
     before
    -1.96
     Despite
    -1.91
     Both
    -1.90
     in
    -1.87
     has
    -1.85
     should
    -1.83
     does
    -1.81
    POSITIVE LOGITS
    廰
    1.62
    
    1.60
     ſmall
    1.60
    ではある
    1.60
     intriguing
    1.59
     elegant
    1.57
    generally
    1.56
    饸
    1.55
    usually
    1.52
    probably
    1.51
    Activations Density 0.001%

    No Known Activations