© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59040
    Prev
    Next
    INDEX
    Explanations

    means 'definition' or 'meaning'

    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
     даже
    -1.52
     nawet
    -1.49
    Después
    -1.47
     geschlagen
    -1.44
    トゥ
    -1.43
    Dentro
    -1.35
    所有的
    -1.30
    我们
    -1.28
     ディ
    -1.23
    食べる
    -1.23
    POSITIVE LOGITS
     when
    1.83
     where
    1.66
     a
    1.51
     we
    1.49
     to
    1.47
     other
    1.43
     from
    1.39
     whereby
    1.39
     would
    1.37
    ellants
    1.33
    Activations Density 0.032%

    No Known Activations