© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 108586
    Prev
    Next
    INDEX
    Explanations

    quantifier followed by of

    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
     exportaciones
    -1.73
     afectada
    -1.63
     embarazada
    -1.63
     negociaciones
    -1.59
     ahorrar
    -1.58
     aislada
    -1.58
     кілька
    -1.53
    絝
    -1.52
     desconto
    -1.52
     gruesa
    -1.48
    POSITIVE LOGITS
     of
    12.75
    ของ
    3.95
     của
    3.25
     των
    2.86
    of
    2.64
     של
    2.61
     ofthe
    2.44
     Of
    2.20
     της
    2.16
    もちろん
    2.09
    Activations Density 0.226%

    No Known Activations