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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5148
    Prev
    Next
    INDEX
    Explanations

    indicating intensity

    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
     tamb
    1.11
    oğlu
    1.11
    ْن
    1.11
    ńczy
    1.09
     tient
    1.08
    รักษา
    1.04
     الأمر
    1.04
    ೋಪ
    1.01
     ro
    1.00
     notepad
    0.99
    POSITIVE LOGITS
    holds
    2.05
     mẽ
    1.89
     contender
    1.63
    烈的
    1.61
     💪
    1.54
    িশালী
    1.50
     contenders
    1.45
     headwinds
    1.43
     convictions
    1.26
     worded
    1.23
    Activations Density 0.166%

    No Known Activations