© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22881
    Prev
    Next
    INDEX
    Explanations

    protect against

    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_40_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
    s
    0.45
    ปลอดภัย
    0.39
    PA
    0.38
    安全
    0.38
    安全的
    0.37
    痛
    0.37
     Wast
    0.37
    r
    0.37
    jährigen
    0.36
    SA
    0.36
    POSITIVE LOGITS
     against
    1.21
    against
    1.13
    Against
    0.97
     tegen
    0.93
     AGAINST
    0.93
     Against
    0.92
     contre
    0.91
     ضد
    0.87
     terhadap
    0.86
     gegen
    0.83
    Activations Density 0.003%

    No Known Activations