© 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. 68046
    Prev
    Next
    INDEX
    Explanations

    exactly what

    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
    งิน
    -1.41
     unſ
    -1.34
    躂
    -1.33
     alimente
    -1.33
    
    -1.29
     bahkan
    -1.27
    蹀
    -1.27
    chastic
    -1.27
    koszulka
    -1.25
    鼇
    -1.25
    POSITIVE LOGITS
     that
    2.16
     those
    1.95
     what
    1.88
     this
    1.44
     are
    1.34
     these
    1.32
     makes
    1.31
     now
    1.30
    正是
    1.29
     keeps
    1.28
    Activations Density 0.016%

    No Known Activations