© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43026
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     that
    -2.11
     slecht
    -1.56
     eenvoudig
    -1.56
    無事に
    -1.49
     ficaram
    -1.48
    FOREWORD
    -1.46
    协助
    -1.41
     épreuves
    -1.40
    暖かい
    -1.38
     valmist
    -1.37
    POSITIVE LOGITS
     to
    1.75
     It
    1.63
     pidana
    1.32
    PasswordEncoder
    1.31
     onFailure
    1.31
    Mutagenicity
    1.30
    聍
    1.30
     The
    1.30
     o
    1.29
    字幕
    1.29
    Activations Density 0.108%

    No Known Activations