© 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. 73766
    Prev
    Next
    INDEX
    Explanations

    short answer summary

    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
     also
    -1.62
     even
    -1.30
     may
    -1.17
     might
    -1.12
     further
    -1.03
     some
    -1.00
     additionally
    -0.99
     can
    -0.98
     left
    -0.98
     especially
    -0.98
    POSITIVE LOGITS
    結論
    1.59
     summary
    1.31
    Summary
    1.28
    总体
    1.25
     nutshell
    1.23
     overarching
    1.23
    overall
    1.21
    primarily
    1.20
     общем
    1.20
     feront
    1.20
    Activations Density 0.132%

    No Known Activations