© 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. 47694
    Prev
    Next
    INDEX
    Explanations

    causing damage or negative effects

    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
    ?
    -2.63
    🕗
    -2.39
    iſter
    -2.14
     gouver
    -2.08
    So
    -2.08
     ism
    -2.05
     kaas
    -2.03
     pü
    -2.00
    錘
    -1.98
     {
    -1.96
    POSITIVE LOGITS
    ly
    2.69
     così
    2.36
     to
    2.28
    鹇
    2.20
     perceptive
    2.19
     damaging
    2.03
    🧌
    2.00
    鸶
    1.94
    檠
    1.89
    ﹐
    1.88
    Activations Density 0.016%

    No Known Activations