© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    prepositions and determiners

    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
    følgelig
    -0.86
    Another
    -0.84
    حول
    -0.84
    زال
    -0.82
    Epil
    -0.81
    рных
    -0.80
     leto
    -0.80
     aislada
    -0.79
    There
    -0.79
     кілька
    -0.77
    POSITIVE LOGITS
     of
    4.38
    ของ
    1.56
     của
    1.52
     של
    1.39
    of
    1.28
     των
    1.15
    ủa
    1.02
     giacca
    0.96
     diſt
    0.94
     ſmall
    0.93
    Activations Density 0.053%

    No Known Activations