© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65339
    Prev
    Next
    INDEX
    Explanations

    .edu domains and specific characters

    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
    !"
    -2.08
     другие
    -2.03
    ];
    -2.00
     '
    -1.98
    !)
    -1.94
    %"),
    -1.88
     Incluso
    -1.86
    ᪥
    -1.86
     nové
    -1.83
    ]);
    -1.81
    POSITIVE LOGITS
    ↵↵
    2.11
    鱟
    1.96
    »?
    1.79
    تال
    1.77
     riu
    1.76
     itſelf
    1.75
    ܖ
    1.72
     lopez
    1.71
     you
    1.71
     vinyle
    1.69
    Activations Density 0.003%

    No Known Activations