© 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-65K
    7. 1056
    Prev
    Next
    INDEX
    Explanations

    quotation marks or contractions

    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_65k_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
     ব্যাকটেরিয়া
    1.37
    xssf
    1.36
    feasible
    1.32
    <unused686>
    1.31
    <unused1196>
    1.29
    compressible
    1.29
    <unused981>
    1.27
    xcodep
    1.26
     PHASE
    1.25
    <unused1857>
    1.24
    POSITIVE LOGITS
    あるいは
    1.13
     narrator
    1.07
     Ray
    1.05
     slump
    1.05
    カール
    1.04
    パッド
    1.02
    一人
    1.02
     koment
    1.02
    ちょっと
    1.00
    عد
    1.00
    Activations Density 0.154%

    No Known Activations