© 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. 22-GEMMASCOPE-RES-131K
    7. 38680
    Prev
    Next
    INDEX
    Explanations

    being used or described

    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_22/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
    It
    -1.21
     It
    -1.01
    留言
    -0.99
     Inggris
    -0.97
     aktivi
    -0.97
    спек
    -0.95
     Prancis
    -0.93
     muuta
    -0.93
    тория
    -0.91
    zler
    -0.91
    POSITIVE LOGITS
     there
    1.40
     exists
    1.30
     exist
    1.27
     included
    1.20
     available
    1.19
     present
    1.16
     same
    1.16
    べし
    1.04
     possibilities
    1.04
     happening
    1.03
    Activations Density 0.127%

    No Known Activations