© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    block followed by punctuation or "of"

    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
    〮
    -1.63
    ’
    -1.63
    慤
    -1.50
    焿
    -1.49
     涂
    -1.49
    rified
    -1.49
    0
    -1.49
    
    -1.48
    elerik
    -1.45
    jewództ
    -1.43
    POSITIVE LOGITS
     यदि
    2.23
     может
    1.89
    ];
    1.87
    )),
    1.84
    S
    1.81
    内で
    1.79
    })
    1.79
    ":"
    1.77
     ними
    1.77
    )]
    1.72
    Activations Density 0.014%

    No Known Activations