© 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. 2900
    Prev
    Next
    INDEX
    Explanations

    finding responsibilities

    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
    zelfde
    2.00
    ాన్ని
    1.89
    ej
    1.80
    ઓના
    1.69
    یع
    1.57
     nedenle
    1.56
    ی
    1.54
    eight
    1.52
    yld
    1.51
    𝘭
    1.51
    POSITIVE LOGITS
    ibilities
    1.76
     affliction
    1.51
     circumstances
    1.46
    ////////////////
    1.42
    ค์
    1.37
     Conjug
    1.35
     Obviously
    1.34
    λης
    1.33
    িয়া
    1.33
    टीएम
    1.33
    Activations Density 0.008%

    No Known Activations