© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 4364
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )](
    1.03
    giveness
    0.99
    <unused407>
    0.94
    .!
    0.94
    ホ
    0.92
    inflation
    0.92
    <unused1224>
    0.92
    🔯
    0.90
    <h5>
    0.90
     rejuven
    0.90
    POSITIVE LOGITS
     उसमें
    0.78
     one
    0.70
     fleste
    0.70
     daarmee
    0.67
    有两个
    0.66
     उसमे
    0.65
     বলেছি
    0.63
     চালাতে
    0.62
    and
    0.62
    ូន
    0.62
    Activations Density 0.824%

    No Known Activations