© 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. 9903
    Prev
    Next
    INDEX
    Explanations

    URL encoding and separators

    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
    єте
    1.32
     ১৯৯
    1.31
    <blockquote>
    1.30
     scourge
    1.30
    Miscellaneous
    1.30
    Indexer
    1.29
     spaceleft
    1.27
    <unused381>
    1.27
     دسته
    1.25
    ABILITIES
    1.25
    POSITIVE LOGITS
     also
    1.11
    en
    1.10
    cu
    1.02
    id
    1.00
    的面
    0.94
    에
    0.94
     pot
    0.91
     passed
    0.91
    enso
    0.89
    也被
    0.88
    Activations Density 0.009%

    No Known Activations