© 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. 19177
    Prev
    Next
    INDEX
    Explanations

    complete the

    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
    〬
    -2.34
    
    -2.34
     peculiarities
    -2.23
     dando
    -2.17
    .
    -2.13
     mostrarán
    -2.13
     dents
    -2.08
     overt
    -2.08
     każ
    -2.03
     stalwart
    -2.02
    POSITIVE LOGITS
    鯪
    2.63
     белом
    2.56
    棪
    2.53
    菔
    2.39
     stehe
    2.38
     dirigez
    2.38
    䊏
    2.38
    n
    2.34
    ꗃ
    2.34
    豋
    2.27
    Activations Density 0.017%

    No Known Activations