© 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. 34-GEMMASCOPE-RES-131K
    7. 63844
    Prev
    Next
    INDEX
    Explanations

    Q: answered questions

    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_34/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
     for
    -1.81
     before
    -1.58
     three
    -1.55
     after
    -1.52
     give
    -1.50
     because
    -1.49
     using
    -1.49
     two
    -1.47
     gave
    -1.45
     partly
    -1.45
    POSITIVE LOGITS
     ADDITIONAL
    1.43
     exceedingly
    1.41
    镲
    1.38
     astounding
    1.36
     😊
    1.35
     certamente
    1.34
     incredibly
    1.33
     exceptionally
    1.32
     pernic
    1.31
     dessa
    1.30
    Activations Density 0.040%

    No Known Activations