© 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. 73775
    Prev
    Next
    INDEX
    Explanations

    highly-rated, leading, best

    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
     for
    -1.33
     other
    -1.26
    其它
    -1.24
     otras
    -1.21
    Other
    -1.21
    的其他
    -1.17
     altre
    -1.16
    其他的
    -1.16
     it
    -1.15
    其他
    -1.15
    POSITIVE LOGITS
     who
    1.74
     in
    1.47
    portug
    1.39
    fraid
    1.38
    nachron
    1.35
    dsquared
    1.26
     estadounid
    1.25
    contemporary
    1.23
    moderne
    1.23
     čaj
    1.21
    Activations Density 0.045%

    No Known Activations