© 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. 92945
    Prev
    Next
    INDEX
    Explanations

    American football teams, cities

    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
    Ouest
    -0.71
    нин
    -0.68
    езда
    -0.68
    菱
    -0.67
    KOS
    -0.67
    aito
    -0.67
    preter
    -0.66
     przen
    -0.65
    篱
    -0.65
    сия
    -0.65
    POSITIVE LOGITS
     breakaway
    1.01
     Spring
    0.80
     spring
    0.79
     Frühling
    0.77
    spring
    0.75
    missive
    0.74
    ofor
    0.74
     SPRING
    0.73
    сить
    0.73
     воз
    0.73
    Activations Density 0.031%

    No Known Activations