© 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. 103323
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases and reversals

    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
     this
    -1.58
    _
    -1.51
     adequate
    -1.51
     særlig
    -1.42
     there
    -1.41
     ONLY
    -1.41
     in
    -1.41
     only
    -1.36
     an
    -1.35
     because
    -1.35
    POSITIVE LOGITS
     utilisé
    1.89
     usado
    1.79
     trouvé
    1.63
     dentro
    1.63
    potentially
    1.50
    埽
    1.49
     ไม่
    1.49
    踯
    1.48
    崀
    1.47
    foreach
    1.46
    Activations Density 0.028%

    No Known Activations