© 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. 45897
    Prev
    Next
    INDEX
    Explanations

    generic, abs, Arizona, ERP, still

    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
    ब
    0.47
    Taxi
    0.47
    Appropri
    0.44
    Deutschland
    0.44
    -
    0.44
    Ni
    0.43
    Rah
    0.43
    /
    0.43
    Sab
    0.42
     olay
    0.42
    POSITIVE LOGITS
     progressed
    0.45
     យើង
    0.45
    ську
    0.44
     It
    0.44
    ামুটি
    0.43
    ዶች
    0.43
    ंसारी
    0.43
     နှစ်
    0.42
    ằm
    0.42
     ဆို
    0.42
    Activations Density 0.000%

    No Known Activations