© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1318
    Prev
    Next
    INDEX
    Explanations

    states of being or emotion

    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
     делает
    -1.10
     любую
    -1.05
    deauna
    -1.03
     compleja
    -1.02
     borrar
    -1.02
    戋
    -1.01
     разные
    -1.00
    Зно
    -0.98
     arreglar
    -0.98
    羕
    -0.97
    POSITIVE LOGITS
     of
    6.91
     that
    2.52
    ของ
    2.33
     của
    1.85
     associated
    1.59
     של
    1.57
    of
    1.45
     της
    1.38
    associated
    1.24
     siitä
    1.23
    Activations Density 0.046%

    No Known Activations