© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13774
    Prev
    Next
    INDEX
    Explanations

    events and entertainment

    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
    5
    -1.89
    feliz
    -1.61
    
    -1.60
    2
    -1.56
     Beginner
    -1.55
     薬局
    -1.49
    regarding
    -1.48
    anyway
    -1.47
    various
    -1.45
    Ꮠ
    -1.45
    POSITIVE LOGITS
     one
    1.76
     Both
    1.63
     now
    1.57
     Gedanke
    1.56
     each
    1.56
     like
    1.52
     unparalleled
    1.51
     for
    1.51
     Like
    1.49
     with
    1.45
    Activations Density 0.002%

    No Known Activations