© 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. 15892
    Prev
    Next
    INDEX
    Explanations

    Your followed by a descriptive.[DONE]

    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
     znacz
    0.82
     tradisional
    0.81
     prepend
    0.76
    ധി
    0.73
    bounds
    0.72
    Causes
    0.71
     generality
    0.71
     thu
    0.70
    像
    0.69
    STY
    0.68
    POSITIVE LOGITS
     congratulate
    0.99
    ഓ
    0.97
    sponsor
    0.97
    oce
    0.96
     Mitochond
    0.95
    𝐧
    0.94
     رمز
    0.94
     deton
    0.94
     বাইরে
    0.93
    observer
    0.93
    Activations Density 0.009%

    No Known Activations