© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19690
    Prev
    Next
    INDEX
    Explanations

    timing and occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ੀ
    0.42
    ਜ਼
    0.41
    ਾ
    0.41
    tube
    0.40
    ovsk
    0.40
    Semitism
    0.40
     результатом
    0.40
     संबंधित
    0.40
    inflammation
    0.40
    ход
    0.40
    POSITIVE LOGITS
     damals
    0.47
     damal
    0.42
     NEVER
    0.41
    !।
    0.41
     irgendwie
    0.40
    !!!!!!
    0.40
    ،
    0.40
    当时
    0.39
    !!!!
    0.39
     المرح
    0.39
    Activations Density 0.005%

    No Known Activations