© 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. 31159
    Prev
    Next
    INDEX
    Explanations

    html attributes

    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
     id
    -0.98
     technisch
    -0.95
     الاجتماعي
    -0.95
     titulado
    -0.89
     Iglesia
    -0.89
    withId
    -0.86
     dumbfounded
    -0.86
     intolerable
    -0.83
     idiota
    -0.82
    id
    -0.81
    POSITIVE LOGITS
    ään
    0.91
    跬
    0.75
     mangas
    0.75
    をはじめ
    0.75
    ın
    0.75
     Ө
    0.74
     посо
    0.73
    ắc
    0.72
     tahun
    0.71
     carros
    0.71
    Activations Density 0.020%

    No Known Activations