© 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-16K
    7. 3206
    Prev
    Next
    INDEX
    Explanations

    kind of description

    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
    Negative Logits
     являются
    0.88
     irrespective
    0.87
    必ず
    0.87
     regardless
    0.83
    так
    0.82
     відповідно
    0.82
     प्रदान
    0.82
     반드시
    0.81
    <unused434>
    0.81
     myocardium
    0.80
    POSITIVE LOGITS
     thing
    1.85
     kinda
    1.78
     kind
    1.70
     sorta
    1.45
     stuff
    1.45
     kinds
    1.38
     sort
    1.38
     sortes
    1.29
     guys
    1.28
    みたいな
    1.27
    Activations Density 0.091%

    No Known Activations