© 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. 68897
    Prev
    Next
    INDEX
    Explanations

    conversational starters and explanations

    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
    </i>
    -1.62
    endfor
    -1.49
    >
    -1.38
    liegende
    -1.37
    reportWebVitals
    -1.35
    yyj
    -1.35
    yyb
    -1.34
    lenovo
    -1.33
    malige
    -1.32
    laboration
    -1.31
    POSITIVE LOGITS
     although
    1.57
     partly
    1.45
     currently
    1.40
     newly
    1.39
     if
    1.37
     or
    1.36
     partially
    1.34
     while
    1.32
     because
    1.31
     so
    1.30
    Activations Density 0.094%

    No Known Activations