© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    find help links

    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
    pang
    0.78
    气体
    0.76
     Catch
    0.68
     शव
    0.66
    azón
    0.66
     चेतन
    0.64
     onCreateView
    0.64
    Ղ
    0.63
     स्टी
    0.63
     অস্ত
    0.63
    POSITIVE LOGITS
     sacrifice
    0.99
     runners
    0.98
    sacrifice
    0.85
    runners
    0.85
     Runners
    0.84
     runner
    0.84
    inalis
    0.83
     Sacrifice
    0.82
    eken
    0.81
    runner
    0.81
    Activations Density 0.081%

    No Known Activations