© 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. 29-GEMMASCOPE-2-RES-16K
    7. 3836
    Prev
    Next
    INDEX
    Explanations

    Lang + Chain, tungsten, Pingdom

    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_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     பர
    0.84
    ّر
    0.69
    п
    0.66
     编辑
    0.65
    anlı
    0.65
     Normalize
    0.64
     isotype
    0.63
    க்குள்
    0.63
    崩
    0.62
    ссы
    0.62
    POSITIVE LOGITS
    UAGES
    1.22
    ค์
    1.18
    ladesh
    1.13
    lasses
    1.10
    ्ज
    1.04
    razio
    1.03
    katkan
    1.02
    lades
    0.98
    ratulations
    0.97
    tang
    0.95
    Activations Density 0.124%

    No Known Activations