© 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. 321
    Prev
    Next
    INDEX
    Explanations

    the + noun

    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
     zgodnie
    1.62
     yet
    1.43
     وذلك
    1.43
     como
    1.36
     intently
    1.34
    ;
    1.34
     Himself
    1.33
     związ
    1.32
    .
    1.32
     tätig
    1.30
    POSITIVE LOGITS
     goal
    2.29
    oretically
    2.18
     aim
    2.18
     reason
    2.13
     purpose
    2.06
     사람은
    2.06
     problem
    2.00
    odore
    1.99
     peculiarity
    1.99
     onus
    1.96
    Activations Density 2.541%

    No Known Activations