© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13626
    Prev
    Next
    INDEX
    Explanations

    ставить, put, installation

    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
    蒾
    -1.95
    fficking
    -1.79
    кладка
    -1.76
    }
    -1.69
    昳
    -1.63
    嫱
    -1.63
    柃
    -1.57
     套装
    -1.55
     沙
    -1.52
    phylococcus
    -1.52
    POSITIVE LOGITS
    </strong>
    2.41
    ”;
    1.83
    </u>
    1.81
     analogous
    1.79
     使っ
    1.78
     também
    1.77
    Ⲉ
    1.73
     توانند
    1.67
    .’
    1.63
            
    1.60
    Activations Density 0.003%

    No Known Activations