© 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. 1572
    Prev
    Next
    INDEX
    Explanations

    you want, prefer, need

    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
    ensis
    1.62
     Owing
    1.47
    ulah
    1.46
     dawa
    1.41
    这类
    1.41
     цієї
    1.41
     ovog
    1.40
    蔵
    1.36
     набу
    1.34
    這一
    1.34
    POSITIVE LOGITS
     otherwise
    1.48
    reasonably
    1.43
     reasonably
    1.40
     comfortably
    1.38
     ostensibly
    1.34
     clearly
    1.31
     possibly
    1.28
     normally
    1.27
    otherwise
    1.26
     deems
    1.26
    Activations Density 0.412%

    No Known Activations