© 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. 107016
    Prev
    Next
    INDEX
    Explanations

    sketching and sketches

    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
    を紹介
    -0.92
    不应该
    -0.88
    一句话
    -0.86
     bekam
    -0.85
     commencer
    -0.83
     shimmering
    -0.81
     Bournemouth
    -0.81
    的眼神
    -0.81
    screenshot
    -0.81
     "
    -0.81
    POSITIVE LOGITS
     Sketch
    1.48
     sketch
    1.45
    Sketch
    1.23
    book
    1.19
    books
    1.18
    sketch
    1.17
     sketching
    1.17
     SKETCH
    1.13
     comedy
    1.05
     Sk
    1.05
    Activations Density 0.003%

    No Known Activations