© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26676
    Prev
    Next
    INDEX
    Explanations

    key terminology, sized clinic

    np_acts-logits-general · gemini-2.5-flash-lite

    improve performance, countless creatures, loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    +,
    0.53
     from
    0.48
     with
    0.47
     যখন
    0.47
    と思いますが
    0.46
    %,
    0.44
    がありますが
    0.44
     as
    0.44
     없고
    0.44
     clang
    0.44
    POSITIVE LOGITS
    ܀
    0.55
    ።
    0.54
    。
    0.53
    》。
    0.52
     ។
    0.50
    .“
    0.48
    Begriffsklär
    0.48
    .”
    0.47
    ܂
    0.47
    ."
    0.46
    Activations Density 0.235%

    No Known Activations