© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2322
    Prev
    Next
    INDEX
    Explanations

    status, health, side, volume, code

    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
    म्मीद
    1.30
    跚
    1.24
     ris
    1.24
    isenberg
    1.20
    pyrazine
    1.19
    atrième
    1.18
    ylsulfanyl
    1.17
    歹
    1.17
    eresa
    1.17
     оба
    1.15
    POSITIVE LOGITS
     glyph
    1.36
    ঘর
    1.30
    cloth
    1.28
     Encyclop
    1.28
    iging
    1.25
     เช่น
    1.23
     ឬ
    1.23
     generalizing
    1.22
     ofte
    1.21
     ຫຼື
    1.21
    Activations Density 0.416%

    No Known Activations