© 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. 92822
    Prev
    Next
    INDEX
    Explanations

    Thomas Flynn, photodynamic, compound, movement

    np_acts-logits-general · gemini-2.5-flash-lite

    Android UI components and layout attributes, particularly TextView-related code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ഥ
    -0.76
    ತಿ
    -0.75
     Membran
    -0.68
     circum
    -0.68
     syarat
    -0.67
    詬
    -0.67
    Suitable
    -0.66
    скільки
    -0.66
    ͻ
    -0.66
     kilowatt
    -0.65
    POSITIVE LOGITS
     TextView
    1.02
    compound
    1.02
    movement
    0.96
     compound
    0.94
     movement
    0.93
     Compound
    0.90
    Compound
    0.88
    Movement
    0.86
     movements
    0.85
     Movement
    0.84
    Activations Density 0.022%

    No Known Activations