© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    book divisions

    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
     during
    -1.44
     by
    -1.43
    fficio
    -1.34
     regardless
    -1.27
     through
    -1.27
     from
    -1.23
     at
    -1.20
     confirmó
    -1.19
    
    -1.17
     using
    -1.16
    POSITIVE LOGITS
     chapter
    1.68
     chapters
    1.60
     section
    1.40
    yorsunuz
    1.40
     Presenta
    1.39
     endet
    1.32
     „
    1.30
    Chapter
    1.29
     centrales
    1.27
    Provides
    1.26
    Activations Density 0.044%

    No Known Activations