© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2966
    Prev
    Next
    INDEX
    Explanations

    optional additions

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    1.96
    ﻢ
    1.95
    jahr
    1.88
     upset
    1.85
    वाया
    1.84
    QUENCY
    1.84
     வகையில்
    1.83
     futuras
    1.81
     τ
    1.81
     ihe
    1.79
    POSITIVE LOGITS
    т
    2.97
    ল
    2.56
     acontece
    2.50
     collider
    2.48
    ষুধ
    2.47
    お金
    2.47
    ন
    2.43
    ン
    2.37
     costituito
    2.36
    ν
    2.34
    Activations Density 0.021%

    No Known Activations