© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 106291
    Prev
    Next
    INDEX
    Explanations

    stealing from organizations

    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_16_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
    ту
    0.68
    ни
    0.67
    ন
    0.62
    ে
    0.59
    صار
    0.58
    éph
    0.57
    ну
    0.57
    ción
    0.57
     menú
    0.56
     এল
    0.54
    POSITIVE LOGITS
    Κα
    0.69
    Ма
    0.57
    aling
    0.57
    gers
    0.57
    becue
    0.55
    珊
    0.54
     கோவில
    0.53
     Convenience
    0.53
    ansk
    0.52
     Trouble
    0.52
    Activations Density 0.000%

    No Known Activations