© 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. 90872
    Prev
    Next
    INDEX
    Explanations

    course descriptions

    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
    罍
    -2.02
     bricola
    -1.93
    鐿
    -1.92
    蜮
    -1.84
     ſtate
    -1.73
     There
    -1.72
    昪
    -1.71
    穑
    -1.71
     protocolos
    -1.70
    淠
    -1.68
    POSITIVE LOGITS
    ↵↵
    2.58
    to
    2.50
    ar
    2.45
    9
    2.38
    ll
    2.34
                    
    2.19
    me
    2.14
    in
    2.14
    3
    2.11
    ver
    2.03
    Activations Density 0.018%

    No Known Activations