© 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. 100906
    Prev
    Next
    INDEX
    Explanations

    Southeast Asia Travel Diary

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

    resources and statistics

    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
     curric
    0.49
    Could
    0.47
     colonial
    0.44
     in
    0.44
    CI
    0.44
    AI
    0.42
    0
    0.41
     who
    0.41
     subgroup
    0.40
     kriv
    0.40
    POSITIVE LOGITS
     ആവശ
    0.48
    MiddleLine
    0.48
    enschaft
    0.48
     içeren
    0.48
     Зем
    0.47
     ອ
    0.47
     फ्लिप
    0.47
    érrez
    0.47
    τουργ
    0.47
     इंटरनेट
    0.46
    Activations Density 0.000%

    No Known Activations