© 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-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1589
    Prev
    Next
    INDEX
    Explanations

    .ai, .io, .com websites

    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_17_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
    ↵↵
    1.00
    G
    0.98
    <eos>
    0.97
    T
    0.85
    M
    0.82
    ↵↵↵
    0.75
    ↵↵↵↵
    0.74
    H
    0.74
    は
    0.74
    ...
    0.73
    POSITIVE LOGITS
    𒌋
    1.55
    IVACON
    1.49
    <unused799>
    1.49
    𒌅
    1.45
    ویان
    1.45
    TrackedDevice
    1.43
     বিশ্ববিদ্যালয়
    1.43
    𐰤
    1.42
     hMut
    1.42
    <unused221>
    1.41
    Activations Density 0.001%

    No Known Activations