© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13971
    Prev
    Next
    INDEX
    Explanations

    providing or seeking aid

    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
    '
    -3.20
    鬭
    -2.94
    ꜄
    -2.84
    镦
    -2.70
    釙
    -2.63
    琹
    -2.63
    方法
    -2.53
    蕷
    -2.44
    with
    -2.41
    of
    -2.39
    POSITIVE LOGITS
    趼
    3.19
    
    2.95
    
    2.86
    谖
    2.83
    轫
    2.72
    
    2.53
    
    2.50
    '])
    2.50
    觏
    2.50
    vantaged
    2.48
    Activations Density 0.002%

    No Known Activations