© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3382
    Prev
    Next
    INDEX
    Explanations

    titles before names

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    mutation
    0.71
    Mr
    0.71
     ​​
    0.71
    擬
    0.69
    for
    0.66
    Open
    0.65
     लिए
    0.65
     prof
    0.64
    а
    0.64
    std
    0.63
    POSITIVE LOGITS
     Emeritus
    1.20
    ificante
    1.07
     Gerade
    1.05
    ifting
    1.05
    ใหญ
    1.05
     ấy
    1.02
    หญิง
    1.02
    ларга
    0.99
     Deborah
    0.99
     Ajay
    0.98
    Activations Density 0.108%

    No Known Activations