© 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. 18688
    Prev
    Next
    INDEX
    Explanations

    Reshape, percentages, formulas

    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
     Whatever
    0.90
     l
    0.78
     D
    0.76
     whatever
    0.75
    S
    0.74
     Incentive
    0.74
     Tap
    0.70
     expected
    0.68
     Any
    0.68
     pressure
    0.68
    POSITIVE LOGITS
     लाहिड़ी
    1.15
    φ
    1.11
    রিষ্ঠ
    1.10
     método
    1.06
     ஆராய்ச்ச
    1.04
    
    1.04
    𝑒
    1.03
     divaricatis
    1.03
    ܬܐ
    1.02
    apanicola
    1.01
    Activations Density 0.000%

    No Known Activations