© 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. 130119
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     about
    -1.95
     and
    -1.94
     not
    -1.73
     there
    -1.55
     if
    -1.51
     necessary
    -1.48
     because
    -1.45
     napis
    -1.41
     through
    -1.41
    For
    -1.40
    POSITIVE LOGITS
    Ruju
    1.56
    
    1.53
    髕
    1.52
     ทำ
    1.48
     flera
    1.48
    bluza
    1.48
     våra
    1.47
    下来的
    1.47
    效应
    1.45
     sommar
    1.45
    Activations Density 0.013%

    No Known Activations