© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    respective items in groups

    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
     is
    -2.14
     if
    -2.13
     when
    -1.77
     all
    -1.77
     often
    -1.76
     almost
    -1.66
     ketika
    -1.66
     or
    -1.64
    This
    -1.64
     at
    -1.63
    POSITIVE LOGITS
     разные
    2.11
     olika
    1.97
     respective
    1.94
     różnych
    1.88
     respectivos
    1.80
    different
    1.79
     различни
    1.76
     різних
    1.74
    面白かった
    1.73
     zobac
    1.66
    Activations Density 0.046%

    No Known Activations