© 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. 22-GEMMASCOPE-RES-131K
    7. 26693
    Prev
    Next
    INDEX
    Explanations

    also then

    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_22/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
     instruk
    -1.02
     статус
    -1.01
    mentes
    -0.98
     إذا
    -0.97
     раньше
    -0.95
    「
    -0.93
    -
    -0.92
     klient
    -0.91
    \{
    -0.91
    Although
    -0.90
    POSITIVE LOGITS
    也会
    1.04
     also
    1.01
     nějak
    0.95
    也就
    0.94
     then
    0.94
    ває
    0.90
     arī
    0.90
     fün
    0.89
     desgracia
    0.87
     kilómetros
    0.85
    Activations Density 0.070%

    No Known Activations