© 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. 490
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     jist
    1.19
     bevy
    1.17
     Hawai
    1.12
     Okla
    1.11
     Dewan
    1.09
     angst
    1.08
     &/
    1.08
     korero
    1.05
     Keenan
    1.04
     imbib
    1.02
    POSITIVE LOGITS
     її
    2.36
     ​​
    2.25
     ​​​​
    2.16
     ”,
    2.12
     peculiarities
    2.12
     peculiarity
    2.09
     ?!
    2.08
     °,
    2.06
     interloc
    2.01
    hereinafter
    2.01
    Activations Density 2.929%

    No Known Activations