© 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. 899
    Prev
    Next
    INDEX
    Explanations

    grey

    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
    ↵↵
    -3.92
    
    -3.09
    甃
    -2.84
    ?’
    -2.77
    鸰
    -2.72
     ソックス
    -2.69
    柃
    -2.64
    ”),
    -2.59
    
    -2.58
    拶
    -2.56
    POSITIVE LOGITS
    They
    3.38
    There
    3.31
    It
    3.28
    When
    3.09
    If
    3.02
    You
    3.00
    With
    3.00
    To
    2.98
    部分
    2.95
    )
    2.89
    Activations Density 0.002%

    No Known Activations