© 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. 10-GEMMASCOPE-RES-131K
    7. 90405
    Prev
    Next
    INDEX
    Explanations

    people are doing X

    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_10/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
    \
    -1.51
    libat
    -1.47
     住宅
    -1.43
    ровал
    -1.43
     sometimes
    -1.38
    ২
    -1.35
     joyas
    -1.34
    Jong
    -1.31
    
    -1.30
     şimdi
    -1.28
    POSITIVE LOGITS
     to
    1.83
    </h1>
    1.59
    ：……
    1.38
     you
    1.34
     being
    1.32
     permissible
    1.32
    </i>
    1.31
    がついて
    1.30
     вещь
    1.27
    ність
    1.24
    Activations Density 0.028%

    No Known Activations