© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2498
    Prev
    Next
    INDEX
    Explanations

    washes away

    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_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
     odnosno
    0.87
    atau
    0.84
    lumat
    0.82
    ‌.
    0.79
     (!)
    0.78
     অনুষ্ঠিত
    0.78
    😐
    0.77
    (!)
    0.77
    skiy
    0.75
     ossia
    0.75
    POSITIVE LOGITS
    不仅
    1.90
    不僅
    1.70
     both
    1.62
     BOTH
    1.58
    뿐
    1.55
    だけでなく
    1.53
     גם
    1.50
     både
    1.50
     nejen
    1.49
     also
    1.44
    Activations Density 0.346%

    No Known Activations