© 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. 99295
    Prev
    Next
    INDEX
    Explanations

    season, country, responsibility

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

    programming editors and keywords

    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
    ঠি
    0.46
    dlg
    0.46
     anche
    0.44
     seguro
    0.44
    đ
    0.44
     excels
    0.43
     especial
    0.43
    quan
    0.43
     impegno
    0.42
    hele
    0.42
    POSITIVE LOGITS
     నొప్పి
    0.54
     สูตร
    0.53
     ควร
    0.48
     Spinach
    0.46
     komponen
    0.46
     Crunch
    0.45
     {}>,
    0.45
    AreEqual
    0.45
     конденса
    0.44
     เริ่ม
    0.44
    Activations Density 0.001%

    No Known Activations