© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92264
    Prev
    Next
    INDEX
    Explanations

    exaggeration or stretching

    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
     Shale
    -0.80
     avea
    -0.80
     nulle
    -0.79
    frust
    -0.79
     inutile
    -0.78
    INCIP
    -0.76
     reprez
    -0.75
    )!=
    -0.75
    のだろう
    -0.73
     vedea
    -0.73
    POSITIVE LOGITS
     stretch
    4.53
     Stretch
    3.69
    stretch
    3.66
    Stretch
    3.36
     stretching
    3.36
     stretches
    3.23
     stretched
    2.78
    stret
    2.67
     Stretching
    2.52
    Stret
    2.50
    Activations Density 0.024%

    No Known Activations