© 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. 68955
    Prev
    Next
    INDEX
    Explanations

    online chat

    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
    蠓
    -2.67
    厹
    -2.42
    鸲
    -2.41
    vantaged
    -2.33
    seamnă
    -2.30
    ✺
    -2.28
     レア
    -2.28
    咈
    -2.27
     jejich
    -2.25
    泐
    -2.23
    POSITIVE LOGITS
    y
    2.78
    }
    2.63
     unwavering
    2.56
    `
    2.44
     unrelenting
    2.30
    ᝢ
    2.27
    ar
    2.27
    {
    2.25
    \
    2.20
     When
    2.19
    Activations Density 0.009%

    No Known Activations