© 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. 2946
    Prev
    Next
    INDEX
    Explanations

    Spanish and Russian endings

    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
    Negative Logits
    讓
    2.09
    uter
    2.00
     کی
    1.97
     větš
    1.91
    Zie
    1.88
    يفة
    1.87
     sich
    1.85
     dibagi
    1.85
     نے
    1.83
     eens
    1.82
    POSITIVE LOGITS
    theless
    3.52
    an
    3.03
    es
    2.83
    ️
    2.75
    nya
    2.70
    ת
    2.68
    adays
    2.66
    in
    2.62
    ো
    2.61
    л
    2.57
    Activations Density 0.032%

    No Known Activations