© 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. 22-GEMMASCOPE-2-RES-262K
    7. 10851
    Prev
    Next
    INDEX
    Explanations

    words ending with a

    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_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    getLong
    1.02
    Tabuleiro
    1.01
     اصلاح
    1.00
    𝑈
    0.99
     overlaps
    0.99
    厶
    0.98
    𝕜
    0.96
    是一名
    0.95
    Update
    0.95
    পরে
    0.94
    POSITIVE LOGITS
    Բ
    1.15
     veel
    1.10
    воен
    1.09
     fundador
    1.09
     noch
    1.09
    ванні
    1.08
     nors
    1.08
     geen
    1.05
     मोटरसाइकिल
    1.04
     विनय
    1.04
    Activations Density 0.000%

    No Known Activations