© 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. 54381
    Prev
    Next
    INDEX
    Explanations

    bypassing policies or instructions

    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
    ו
    0.48
    ಹಿ
    0.48
    ිරි
    0.44
    流域
    0.42
    رب
    0.41
    ೀ
    0.41
    地方
    0.41
    adaptation
    0.41
    HOB
    0.41
    umum
    0.41
    POSITIVE LOGITS
    :
    0.49
     is
    0.47
     vena
    0.47
     caj
    0.45
     tangible
    0.44
     rent
    0.44
     durable
    0.43
     cấp
    0.43
     sembl
    0.43
     қол
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.