© 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. 73180
    Prev
    Next
    INDEX
    Explanations

    creation and making

    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
     wersji
    -2.14
    年
    -2.06
    屃
    -2.02
     PLAST
    -1.98
     victoires
    -1.93
     OGSÅ
    -1.89
     pérd
    -1.86
     GERMANY
    -1.83
     czter
    -1.82
    赑
    -1.82
    POSITIVE LOGITS
     ‘
    1.94
    t
    1.77
     unmöglich
    1.74
     If
    1.73
     “…
    1.73
     Could
    1.71
     They
    1.68
     “
    1.66
    ”.
    1.66
     Easily
    1.65
    Activations Density 0.006%

    No Known Activations