© 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. 10-GEMMASCOPE-RES-131K
    7. 8521
    Prev
    Next
    INDEX
    Explanations

    intensifying adjectives

    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
     such
    -2.16
     continually
    -1.73
    䊐
    -1.55
    ようですが
    -1.49
    primarily
    -1.45
    のですね
    -1.43
    mainly
    -1.36
     eventually
    -1.36
     angeschlossen
    -1.35
    originally
    -1.34
    POSITIVE LOGITS
    With
    1.72
    There
    1.48
     three
    1.48
     Extremely
    1.48
     With
    1.45
     two
    1.45
     école
    1.45
    、
    1.45
    〰
    1.40
    Very
    1.39
    Activations Density 0.056%

    No Known Activations