© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4408
    Prev
    Next
    INDEX
    Explanations

    good practice

    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
    ܐ
    1.57
     Alte
    1.56
    àng
    1.53
    ändige
    1.52
    ادی
    1.50
    اپ
    1.48
     minify
    1.47
    їз
    1.46
    populate
    1.46
     opium
    1.46
    POSITIVE LOGITS
    head
    0.98
    eyed
    0.96
    `);
    0.88
    而言
    0.87
     kalem
    0.85
    nuts
    0.84
     Coleoptera
    0.83
    legs
    0.83
    に必要な
    0.83
    heads
    0.82
    Activations Density 0.020%

    No Known Activations