© 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. 42785
    Prev
    Next
    INDEX
    Explanations

    moving in

    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
    赑
    -1.85
    到来
    -1.68
    啸
    -1.63
    𖡼
    -1.57
    蹕
    -1.53
    ࿆
    -1.52
    哟
    -1.50
    <td>
    -1.46
    巔
    -1.41
     아이콘
    -1.40
    POSITIVE LOGITS
    </em>
    1.95
     dekoratif
    1.63
     verfügen
    1.48
     fantastic
    1.48
     waż
    1.47
    </strong>
    1.47
     durchaus
    1.46
     poë
    1.45
    }.
    1.45
     incredibly
    1.45
    Activations Density 0.029%

    No Known Activations