© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1023
    Prev
    Next
    INDEX
    Explanations

    ordering or authorizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    妈妈
    0.76
     kotak
    0.72
     bitrate
    0.71
     ক্ষেত্রে
    0.70
     درجة
    0.70
    掙
    0.69
    িয়ের
    0.69
    幫
    0.68
     মায়ের
    0.68
    靠近
    0.68
    POSITIVE LOGITS
    吩
    1.25
     instructing
    1.21
     hiring
    1.19
     instructs
    1.18
     ordering
    1.18
     ordered
    1.17
     authorize
    1.16
    สั่ง
    1.16
    ordering
    1.15
    instruct
    1.13
    Activations Density 0.126%

    No Known Activations