© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71260
    Prev
    Next
    INDEX
    Explanations

    lord hegemony warlord

    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
     '
    -3.02
    '
    -2.95
    榈
    -2.42
    ’
    -2.28
     \"
    -2.27
    ]."
    -2.02
    ,\\
    -2.00
     verheir
    -1.97
    …"
    -1.95
     gewiß
    -1.92
    POSITIVE LOGITS
     During
    1.88
        
    1.86
     Each
    1.84
    𝘁
    1.81
     Throughout
    1.76
    As
    1.73
     and
    1.73
    ܜ
    1.73
    ’.
    1.71
     mempengaruhi
    1.71
    Activations Density 0.001%

    No Known Activations