© 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. 86726
    Prev
    Next
    INDEX
    Explanations

    all over

    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
    </b>
    -2.20
    </td>
    -2.03
     is
    -1.80
    ");
    -1.78
     gleiche
    -1.72
    </h5>
    -1.67
     этом
    -1.63
    \
    -1.61
     delantera
    -1.59
     vollständige
    -1.55
    POSITIVE LOGITS
    　　【
    1.77
    𖣘
    1.55
    ه
    1.54
    ي
    1.53
    ên
    1.52
    鬟
    1.49
     ‘‘
    1.48
     encompassing
    1.47
     henne
    1.46
    春天
    1.46
    Activations Density 0.013%

    No Known Activations