© 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. 124129
    Prev
    Next
    INDEX
    Explanations

    positive adjectives for people and things

    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
     of
    -1.62
     instead
    -1.60
     anstatt
    -1.49
     others
    -1.42
     how
    -1.34
     innych
    -1.32
     ähnlichen
    -1.30
     into
    -1.28
     particolare
    -1.26
     angefangen
    -1.26
    POSITIVE LOGITS
     and
    1.52
     trasero
    1.39
     食堂
    1.35
    嵯
    1.34
     who
    1.34
    澳大利
    1.34
    滋賀
    1.32
    石垣
    1.30
    Aunque
    1.27
    絵本
    1.27
    Activations Density 0.056%

    No Known Activations