© 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. 106568
    Prev
    Next
    INDEX
    Explanations

    group of people or country

    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
     of
    -2.19
     itself
    -1.51
     we
    -1.19
    itself
    -1.09
     manquante
    -1.05
     you
    -1.05
    なのかな
    -0.98
    様の
    -0.96
     ГОСТ
    -0.96
     verfügen
    -0.94
    POSITIVE LOGITS
     selves
    1.09
     органы
    1.06
    likation
    1.05
    restaurant
    1.01
     counterparts
    0.98
     sirvió
    0.98
    friends
    0.98
    mates
    0.95
     nieces
    0.95
     детства
    0.94
    Activations Density 0.077%

    No Known Activations