© 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. 17-GEMMASCOPE-2-RES-16K
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    challenge yourself

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    panic
    2.51
    smanship
    2.51
    HttpSession
    2.49
    ties
    2.45
    िक
    2.36
    discuss
    2.25
    prevState
    2.24
    stake
    2.24
     ${{
    2.21
    ዀ
    2.16
    POSITIVE LOGITS
    生素
    2.32
     собой
    2.16
    𝗿
    2.12
     Scotch
    2.06
    ीन
    2.03
    ें
    2.01
    റ
    1.92
     hail
    1.91
    𝗻
    1.90
    atisf
    1.90
    Activations Density 0.042%

    No Known Activations