© 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-16K
    7. 2611
    Prev
    Next
    INDEX
    Explanations

    city, county, and region names

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TorpedoStore
    1.08
    Donc
    1.02
    entesque
    1.02
    quarie
    0.96
     '&
    0.94
    ہ
    0.93
     Seja
    0.91
    ÓN
    0.90
     mistress
    0.90
    дравствуйте
    0.90
    POSITIVE LOGITS
     dàng
    1.09
     цей
    1.03
     الاخت
    1.00
    פ
    0.98
     срок
    0.97
    seater
    0.92
     اطلع
    0.91
     oblivion
    0.89
     annihil
    0.89
     asymptotically
    0.89
    Activations Density 0.049%

    No Known Activations