© 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. 39292
    Prev
    Next
    INDEX
    Explanations

    names followed by titles or surnames

    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
    ....
    -1.47
     only
    -1.47
     /
    -1.45
    ….
    -1.44
     our
    -1.42
     by
    -1.38
    !!!!
    -1.37
    ......
    -1.37
    !!!
    -1.36
    .......
    -1.34
    POSITIVE LOGITS
     reager
    1.65
     siè
    1.52
     pistolet
    1.49
     inond
    1.48
     constater
    1.44
     gangen
    1.43
    футболка
    1.41
    づらい
    1.39
    bánh
    1.39
     bénéfice
    1.38
    Activations Density 0.036%

    No Known Activations