© 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. 58153
    Prev
    Next
    INDEX
    Explanations

    on followed by location or object

    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
    sist
    -0.80
    newInstance
    -0.80
     зрения
    -0.79
     اللون
    -0.78
     mitra
    -0.77
     musik
    -0.76
    లో
    -0.75
    Ậ
    -0.75
    Figures
    -0.75
    тъ
    -0.73
    POSITIVE LOGITS
     walls
    1.47
     forehead
    1.18
     packaging
    1.03
     buildings
    1.02
     wall
    0.99
     each
    0.99
     gravest
    0.98
     etiquetas
    0.97
     door
    0.95
    walls
    0.95
    Activations Density 0.070%

    No Known Activations