© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    summarize and condense text

    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
     TRAILS
    1.24
     SYSTEM
    1.23
     railings
    1.21
     FOR
    1.16
    ::::::
    1.16
    SYSTEM
    1.15
     ...(
    1.13
    FOR
    1.11
    ssystem
    1.10
    ::::
    1.10
    POSITIVE LOGITS
    ity
    1.44
     каче
    1.22
    itarian
    1.15
    itati
    1.14
     excellence
    1.13
     inaccuracy
    1.12
     quality
    1.12
     timeliness
    1.12
    haut
    1.11
     veracity
    1.11
    Activations Density 0.109%

    No Known Activations