© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 169786
    Prev
    Next
    INDEX
    Explanations

    ages and ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    年龄
    0.55
     ≥
    0.47
     younger
    0.46
    年纪
    0.46
     minimum
    0.43
     Younger
    0.43
     mindestens
    0.43
    minimum
    0.43
    若い
    0.42
    年齢
    0.42
    POSITIVE LOGITS
     voi
    0.42
    platte
    0.42
    Ten
    0.42
    मधून
    0.41
     પતિ
    0.41
    تاة
    0.39
    婼
    0.39
     meses
    0.38
    szön
    0.38
     marito
    0.38
    Activations Density 0.009%

    No Known Activations