© 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. 72999
    Prev
    Next
    INDEX
    Explanations

    addressing readers

    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
    </h4>
    -1.78
    ים
    -1.66
    々は
    -1.54
    i
    -1.53
    я
    -1.52
     not
    -1.48
     they
    -1.48
    …”
    -1.45
    ी
    -1.38
    ….
    -1.36
    POSITIVE LOGITS
     extraordinaire
    1.88
    ୪
    1.77
    翆
    1.65
    
    1.63
     disminución
    1.63
     readers
    1.62
    jaqueta
    1.61
    えっ
    1.59
    
    1.59
     тільки
    1.58
    Activations Density 0.016%

    No Known Activations