© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1568
    Prev
    Next
    INDEX
    Explanations

    Rust code and comments

    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
     CX
    1.29
     SPT
    1.24
     المغرب
    1.16
    CX
    1.14
    麝
    1.13
     Cusco
    1.11
     CTA
    1.11
    Peru
    1.07
    Bois
    1.05
    桂
    1.04
    POSITIVE LOGITS
     eprintln
    1.36
     Mut
    1.36
    !("{
    1.35
     Finley
    1.35
    !("{}",
    1.31
    !("{:
    1.30
     Pog
    1.30
    println
    1.27
     Morty
    1.26
     &[
    1.23
    Activations Density 0.006%

    No Known Activations