© 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. 78727
    Prev
    Next
    INDEX
    Explanations

    Excuse, pardon, forgive

    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
    ANTAGES
    -0.84
     дает
    -0.84
     overras
    -0.84
     appreciation
    -0.81
     як
    -0.81
     unangemessene
    -0.79
    langle
    -0.79
    OLOGÍA
    -0.79
     unangemess
    -0.79
     veldig
    -0.78
    POSITIVE LOGITS
     Excuse
    1.58
    excuse
    1.56
     pardon
    1.55
    Excuse
    1.52
    Pardon
    1.41
     excuse
    1.38
    pardon
    1.36
     excused
    1.34
     Pardon
    1.32
     for
    1.27
    Activations Density 0.014%

    No Known Activations