© 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. 92639
    Prev
    Next
    INDEX
    Explanations

    sentence endings and new clauses

    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
     however
    -2.08
     Cependant
    -1.77
    However
    -1.68
     echter
    -1.65
    however
    -1.61
     kuitenkin
    -1.61
     whilst
    -1.52
    Whilst
    -1.43
     также
    -1.41
     jedoch
    -1.35
    POSITIVE LOGITS
     That
    1.60
     Except
    1.55
     that
    1.52
     And
    1.47
     which
    1.46
     Then
    1.46
     no
    1.40
     ("
    1.38
     except
    1.34
     maybe
    1.31
    Activations Density 0.100%

    No Known Activations