© 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-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 3807
    Prev
    Next
    INDEX
    Explanations

    summarization, preprocessing, tampered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Include
    1.15
    ˆ
    1.08
    LETIN
    1.07
     Lista
    1.06
    ÍT
    1.04
    レーター
    1.03
    ูณ
    1.03
     comprennent
    1.03
     津
    1.03
    Ÿ
    1.03
    POSITIVE LOGITS
    igated
    1.33
    гон
    1.30
    ogenen
    1.27
    身为
    1.25
    至于
    1.21
    eds
    1.21
    大的
    1.19
    دهای
    1.18
    至於
    1.17
    巨大的
    1.17
    Activations Density 0.132%

    No Known Activations