© 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-65K
    7. 8758
    Prev
    Next
    INDEX
    Explanations

    less than or equal to

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     उच्च
    0.77
     длин
    0.74
     higher
    0.72
     तब्
    0.72
     ロング
    0.71
     முற்ற
    0.70
    Higher
    0.69
    曠
    0.69
    supset
    0.68
     Higher
    0.67
    POSITIVE LOGITS
     less
    1.96
    不超过
    1.96
     Less
    1.73
    ≤
    1.70
     ≤
    1.69
     fewer
    1.64
    Less
    1.63
     LESS
    1.61
    小于
    1.59
    ≲
    1.54
    Activations Density 0.501%

    No Known Activations