© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212401
    Prev
    Next
    INDEX
    Explanations

    who always / are insensitive

    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
    تقرير
    0.40
    ४
    0.39
    AddTo
    0.38
    চ্ছিন্ন
    0.38
    飥
    0.37
     מד
    0.37
    椇
    0.37
    解除
    0.37
    クロス
    0.37
     модуль
    0.37
    POSITIVE LOGITS
     Phillips
    0.42
     Coleman
    0.39
    Phillips
    0.39
     za
    0.38
     Bedeutung
    0.38
     Boyer
    0.38
     revealing
    0.38
     कोशिश
    0.37
     Nash
    0.37
     Policies
    0.37
    Activations Density 0.000%

    No Known Activations