© 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. 1732
    Prev
    Next
    INDEX
    Explanations

    abstraction

    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
    哢
    -2.72
    踽
    -2.47
    because
    -2.47
    澌
    -2.45
    鞴
    -2.36
    
    -2.34
    黉
    -2.33
    <td>
    -2.30
     عف
    -2.23
    an
    -2.22
    POSITIVE LOGITS
     "
    2.94
    萏
    2.86
    ፨
    2.84
    ...
    2.53
    摇了
    2.30
    ㉕
    2.27
     حوالي
    2.22
    ’
    2.17
     immerse
    2.17
    ,"
    2.17
    Activations Density 0.003%

    No Known Activations