© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69698
    Prev
    Next
    INDEX
    Explanations

    laughter and amusement

    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
     on
    -2.19
     you
    -1.98
     a
    -1.80
     the
    -1.60
     any
    -1.52
     when
    -1.43
     out
    -1.41
     menengah
    -1.38
     of
    -1.37
     verbessern
    -1.37
    POSITIVE LOGITS
    hoka
    1.77
    鍆
    1.63
     eficacia
    1.56
     représentent
    1.56
     apparaissent
    1.55
     productividad
    1.48
     GRAT
    1.45
     tiroirs
    1.42
    骉
    1.41
    utsches
    1.40
    Activations Density 0.015%

    No Known Activations