© 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. 36081
    Prev
    Next
    INDEX
    Explanations

    deals changed

    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
    жении
    -0.90
    ("]");
    -0.82
     prominent
    -0.80
    improving
    -0.77
     NOO
    -0.76
     положении
    -0.75
     unrelenting
    -0.74
     invigor
    -0.74
     великолеп
    -0.74
     promoting
    -0.73
    POSITIVE LOGITS
     permissions
    1.14
    kembang
    1.05
     Português
    1.00
     официаль
    0.99
     pratique
    0.96
     São
    0.96
    й
    0.94
     Hardware
    0.93
     Geografia
    0.93
    odly
    0.93
    Activations Density 0.193%

    No Known Activations