© 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. 74928
    Prev
    Next
    INDEX
    Explanations

    HTML attributes

    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
    ⎔
    -2.09
    becomes
    -2.05
    ਲ਼
    -2.00
    镲
    -1.98
    瘣
    -1.95
    ྄
    -1.91
     cinq
    -1.91
     帅气
    -1.90
    ⸨
    -1.88
     手绘
    -1.88
    POSITIVE LOGITS
     with
    2.39
     or
    2.14
    There
    2.13
     was
    2.00
     and
    2.00
     is
    1.97
     again
    1.96
     does
    1.94
    !!!!!
    1.91
    there
    1.89
    Activations Density 0.004%

    No Known Activations