© 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. 87347
    Prev
    Next
    INDEX
    Explanations

    readings and measurements

    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
    ]
    -1.66
    !
    -1.58
     {
    -1.55
    、
    -1.55
    метров
    -1.54
    ,”
    -1.52
    鷓
    -1.48
    </u>
    -1.48
    }
    -1.46
    重的
    -1.45
    POSITIVE LOGITS
    訁
    1.70
    CurtirCurtir
    1.68
     conhecida
    1.67
     keberadaan
    1.63
     diversos
    1.62
     jejich
    1.58
     pierde
    1.56
    嘥
    1.54
    厹
    1.52
    翃
    1.52
    Activations Density 0.042%

    No Known Activations