© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    El followed by Spanish/Catalan words

    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
     대해
    3.06
     대해서
    2.81
    ти
    2.64
    er
    2.60
    प्ताहिक
    2.58
    𝗴
    2.51
     Arrange
    2.44
    在
    2.44
     prostaglandins
    2.42
     annuities
    2.42
    POSITIVE LOGITS
    도
    2.91
    stagram
    2.71
    ся
    2.65
    ので
    2.65
    یت
    2.63
    nya
    2.60
    د
    2.53
    ser
    2.49
    й
    2.49
    ও
    2.45
    Activations Density 0.044%

    No Known Activations