© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14005
    Prev
    Next
    INDEX
    Explanations

    explaining, signifying, or pausing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ↵↵
    1.25
    <start_of_image>
    1.13
    <eos>
    1.02
    ↵↵↵
    1.00
    ↵↵↵↵↵↵
    0.99
    ↵
    0.97
    </h2>
    0.92
    ↵↵↵↵↵
    0.90
    </h5>
    0.89
    ↵↵↵↵
    0.89
    POSITIVE LOGITS
     北欧
    1.56
    ₂(
    1.50
     beetles
    1.50
     Bóng
    1.50
    ᱕
    1.49
    ₂,
    1.48
    benzoimidazole
    1.46
    ួត
    1.46
     destabil
    1.42
     因此
    1.42
    Activations Density 0.001%

    No Known Activations