© 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. 123716
    Prev
    Next
    INDEX
    Explanations

    Fernandez, Hernandez

    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
    鬭
    -2.84
    ?"
    -2.75
    ৹
    -2.56
    ⎚
    -2.47
    樒
    -2.47
    琑
    -2.39
     akty
    -2.36
    
    -2.34
    蕷
    -2.34
    नलोड
    -2.34
    POSITIVE LOGITS
    .
    2.47
    which
    2.44
    </h2>
    2.42
    ?
    2.36
     และ
    2.34
    ↵↵
    2.28
    哢
    2.25
     It
    2.23
    隂
    2.13
    攆
    2.11
    Activations Density 0.002%

    No Known Activations