© 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. 110945
    Prev
    Next
    INDEX
    Explanations

    celebrating achievements or milestones

    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
     or
    -1.95
     to
    -1.73
    或
    -1.63
     any
    -1.62
        
    -1.50
     if
    -1.46
          
    -1.33
    <em>
    -1.31
     for
    -1.25
    );
    -1.23
    POSITIVE LOGITS
    AHULUAN
    1.23
     câmera
    1.23
    AndGet
    1.22
     caneta
    1.22
     belki
    1.20
    質感
    1.20
    Selección
    1.20
    亹
    1.20
    portál
    1.20
    Aç
    1.19
    Activations Density 0.056%

    No Known Activations