© 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. 29394
    Prev
    Next
    INDEX
    Explanations

    inserting or plugging in

    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
    剥
    0.44
    ިން
    0.42
    剝
    0.40
    趄
    0.39
    াপন্ন
    0.39
    转移
    0.38
    oint
    0.37
    盯
    0.37
    kut
    0.37
     corp
    0.37
    POSITIVE LOGITS
     insertion
    1.34
     inserted
    1.33
     inserting
    1.23
     Insertion
    1.17
     insert
    1.16
    插入
    1.14
    insertion
    1.14
     Insert
    1.12
    挿
    1.12
     inser
    1.11
    Activations Density 0.017%

    No Known Activations