© 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. 22-GEMMASCOPE-RES-131K
    4. 39489
    Prev
    Next
    INDEX
    Explanations

    code and text indicators

    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_22/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
     capucha
    -1.52
     cinturón
    -1.45
     cordón
    -1.42
     cojín
    -1.39
     internazionali
    -1.31
    playmobil
    -1.30
     черная
    -1.27
    pantaloni
    -1.25
     colchón
    -1.25
    logotipo
    -1.24
    POSITIVE LOGITS
     cualquier
    1.34
    有些
    1.30
     альбом
    1.27
    我们
    1.26
     will
    1.21
     também
    1.20
     qualquer
    1.20
     спортс
    1.20
    有时候
    1.18
     should
    1.17
    Activations Density 0.000%

    No Known Activations