© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11985
    Prev
    Next
    INDEX
    Explanations

    ego, pride, conceit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    те
    1.56
    ితే
    1.12
    N
    1.10
    теру
    1.05
     материалы
    0.99
    Fit
    0.96
     न
    0.96
     éta
    0.95
    I
    0.95
    декс
    0.94
    POSITIVE LOGITS
     booster
    1.06
     battling
    1.02
     prides
    1.02
     pride
    1.01
     globally
    1.01
     conce
    0.98
     personnalité
    0.98
     egot
    0.98
     disdain
    0.94
    ção
    0.93
    Activations Density 0.109%

    No Known Activations