© 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. 9-GEMMASCOPE-2-RES-262K
    7. 12377
    Prev
    Next
    INDEX
    Explanations

    initiating questions or headings

    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_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     expenditure
    0.97
     carving
    0.96
    нда
    0.94
    liness
    0.91
    这不是
    0.89
     ≤
    0.88
     
    0.88
     magistrates
    0.88
     ≥
    0.88
     α
    0.88
    POSITIVE LOGITS
    já
    1.00
    ું
    0.98
    Для
    0.98
    Ч
    0.96
    rnn
    0.94
    ي
    0.91
    Еще
    0.90
    За
    0.90
    +#+#+
    0.89
    Мо
    0.89
    Activations Density 0.200%

    No Known Activations