© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2427
    Prev
    Next
    INDEX
    Explanations

    left (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymers
    1.15
    osy
    0.99
    leep
    0.98
    ZR
    0.95
    惇
    0.95
    ynn
    0.95
     datar
    0.93
     Jacq
    0.92
    setData
    0.91
    writers
    0.91
    POSITIVE LOGITS
     cruciate
    1.47
     OpenGL
    1.46
     Putnam
    1.38
     dönüş
    1.38
     TensorFlow
    1.37
    PROVIDED
    1.37
    buffalo
    1.35
    Volkswagen
    1.35
    |\
    1.34
     McCann
    1.33
    Activations Density 0.045%

    No Known Activations