© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3945
    Prev
    Next
    INDEX
    Explanations

    media display interfaces

    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
    เป็น
    1.50
    </strong>
    1.34
    es
    1.33
    خان
    1.31
     Mead
    1.29
    ery
    1.28
     Elizabeth
    1.26
    賴
    1.24
    antikan
    1.24
    截至
    1.23
    POSITIVE LOGITS
    swers
    2.10
    chop
    1.81
    istosoma
    1.77
     stry
    1.72
     cris
    1.70
     Jullie
    1.70
     phag
    1.69
    斡
    1.68
    }\!\
    1.68
     bros
    1.67
    Activations Density 0.002%

    No Known Activations