© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38106
    Prev
    Next
    INDEX
    Explanations

    graphics, shading, blend, cull, polygons

    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
     unvaccinated
    -0.71
     Verfahrens
    -0.71
     Datenschutz
    -0.71
    服用
    -0.71
    утбу
    -0.71
    phenols
    -0.70
     cholesterol
    -0.68
     Sahel
    -0.68
    ビール
    -0.66
     меха
    -0.66
    POSITIVE LOGITS
     blend
    1.21
     Blend
    1.18
     Cull
    1.13
    Cull
    1.10
     polygon
    1.09
    Blend
    1.09
    blend
    1.02
     cull
    0.98
    Siv
    0.92
     Polygon
    0.88
    Activations Density 0.010%

    No Known Activations