© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98355
    Prev
    Next
    INDEX
    Explanations

    code syntax fragments

    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
     such
    -1.15
    "",
    -1.02
    such
    -1.02
    酗
    -1.02
     alcune
    -1.00
     conductas
    -1.00
     misschien
    -1.00
     mentre
    -0.99
     takich
    -0.99
    也会
    -0.98
    POSITIVE LOGITS
     you
    1.01
     ((
    1.01
     restaurantes
    0.96
     (
    0.95
     tæn
    0.95
     relojes
    0.94
     dólares
    0.93
    Ꮸ
    0.93
    あなた
    0.93
    ().__
    0.92
    Activations Density 0.003%

    No Known Activations