© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    start of AI response

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ず
    0.57
     многим
    0.56
    zynarod
    0.56
    DVD
    0.56
    इज
    0.54
     учун
    0.54
    cesz
    0.53
     ganancias
    0.53
    Evans
    0.53
    лез
    0.53
    POSITIVE LOGITS
     발생하는
    0.54
     justified
    0.54
     Civilian
    0.54
    :
    0.52
     Generated
    0.52
    生成的
    0.52
     Insertion
    0.51
    其
    0.51
     레
    0.51
     executed
    0.50
    Activations Density 0.107%

    No Known Activations