© 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. 59773
    Prev
    Next
    INDEX
    Explanations

    interior design

    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
    (),
    -2.42
    tedì
    -2.17
     —
    -2.08
    +,
    -1.98
     entsprechende
    -1.95
    м
    -1.91
     proverbial
    -1.89
     笔画
    -1.88
     le
    -1.86
    ];
    -1.81
    POSITIVE LOGITS
    逦
    2.72
     That
    2.41
    が含ま
    2.08
    𓆜
    2.06
     negó
    2.06
     vivido
    2.05
     tocado
    2.03
    ㌧
    1.98
    龵
    1.98
    。『
    1.95
    Activations Density 0.008%

    No Known Activations