© 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. 34-GEMMASCOPE-RES-131K
    7. 63422
    Prev
    Next
    INDEX
    Explanations

    to do

    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_34/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
    rieben
    -0.94
     Doing
    -0.94
     saca
    -0.92
     problemy
    -0.89
    distas
    -0.86
    λες
    -0.85
     Raman
    -0.83
     Ř
    -0.81
     corrupción
    -0.81
    ewski
    -0.80
    POSITIVE LOGITS
     do
    1.88
     did
    1.23
     does
    1.13
     انجام
    0.93
     done
    0.86
    ługość
    0.82
    undes
    0.81
    断了
    0.76
    Lastly
    0.75
    rounding
    0.75
    Activations Density 0.059%

    No Known Activations