© 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. 41-GEMMASCOPE-2-RES-262K
    7. 23425
    Prev
    Next
    INDEX
    Explanations

    ignore restrictions

    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_all/layer_41_width_262k_l0_big
    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
    끙
    0.46
     indirectly
    0.45
     manageable
    0.45
    prevent
    0.43
    还得
    0.43
    olk
    0.42
     stately
    0.42
     prevent
    0.42
     transitions
    0.41
    槌
    0.41
    POSITIVE LOGITS
     disregard
    1.49
     disregarding
    1.46
     disreg
    1.31
     disregarded
    1.29
     unrestricted
    1.16
     ignore
    1.14
     ignoring
    1.11
     Ignoring
    1.06
     Ignore
    1.05
    無視
    1.00
    Activations Density 0.003%

    No Known Activations