© 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. 39587
    Prev
    Next
    INDEX
    Explanations

    leader titles followed by 'of'

    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
     недавно
    -1.80
    咙
    -1.66
    哪个
    -1.66
     haine
    -1.57
     rafraî
    -1.56
     vorsichtig
    -1.55
     rempliss
    -1.54
     dénon
    -1.52
     najlep
    -1.52
     deliciosos
    -1.51
    POSITIVE LOGITS
     for
    2.13
     after
    1.95
     of
    1.95
     about
    1.82
     also
    1.75
     first
    1.60
     this
    1.59
     in
    1.58
     before
    1.55
     at
    1.51
    Activations Density 0.050%

    No Known Activations