© 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. 105700
    Prev
    Next
    INDEX
    Explanations

    create new features

    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
    ご馳走
    -1.65
    ことが多い
    -1.44
     tandis
    -1.44
    ごちそう
    -1.39
    割と
    -1.38
    意外と
    -1.37
     offrant
    -1.36
     bedingt
    -1.34
     récon
    -1.34
     jednego
    -1.34
    POSITIVE LOGITS
     for
    3.63
     in
    2.48
     with
    2.13
     by
    1.99
     для
    1.80
     about
    1.69
     through
    1.60
     when
    1.59
     where
    1.55
     because
    1.51
    Activations Density 0.454%

    No Known Activations