© 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. 238997
    Prev
    Next
    INDEX
    Explanations

    code area

    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
    ade
    0.57
    de
    0.51
     langs
    0.51
    {
    0.49
     forskellige
    0.49
    AIR
    0.48
     of
    0.48
    en
    0.47
    kob
    0.46
    rakk
    0.46
    POSITIVE LOGITS
    ни
    0.47
    рони
    0.46
    עת
    0.46
    🖉
    0.46
     daí
    0.45
    ្សែ
    0.45
    ﺜ
    0.45
    ﹰ
    0.44
     testigo
    0.43
     doGet
    0.43
    Activations Density 0.001%

    No Known Activations