© 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. 13-GEMMASCOPE-2-RES-16K
    4. 8820
    Prev
    Next
    INDEX
    Explanations

    list operations documentation

    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
    对应
    1.32
    对应的
    1.30
    平台
    1.24
     透
    1.23
    落地
    1.22
    坪
    1.21
    迢
    1.21
     配置
    1.21
    精准
    1.19
    lcnaf
    1.19
    POSITIVE LOGITS
    idest
    0.96
     older
    0.95
     barn
    0.94
    previous
    0.94
     Grandpa
    0.92
     viral
    0.92
     Puritan
    0.91
     videot
    0.91
     Citrus
    0.89
    mind
    0.89
    Activations Density 0.010%

    No Known Activations