© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 200936
    Prev
    Next
    INDEX
    Explanations

    avoiding protecting refusing

    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
    oje
    0.55
     აღმასრულ
    0.49
     Zuge
    0.48
    ],$
    0.48
     cementing
    0.46
     enlarging
    0.45
     rebellious
    0.45
     Carlyle
    0.45
     slimy
    0.45
     rougeâtre
    0.45
    POSITIVE LOGITS
    ก
    0.51
    都有
    0.42
    设
    0.42
    canvas
    0.41
    panel
    0.41
    说明
    0.41
     is
    0.40
    ру
    0.40
     با
    0.40
    测试
    0.40
    Activations Density 0.003%

    No Known Activations