© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5091
    Prev
    Next
    INDEX
    Explanations

    emotions and association confusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     为了
    1.87
    tocol
    1.86
     autrefois
    1.83
    }}-
    1.75
     sufrió
    1.73
     \)
    1.72
    ))=\
    1.71
    بول
    1.70
    шила
    1.70
     casse
    1.67
    POSITIVE LOGITS
    就行
    0.95
    udi
    0.89
    を楽し
    0.89
    acting
    0.78
    吧
    0.77
    agner
    0.77
    感じ
    0.76
     nice
    0.74
    igning
    0.74
    agn
    0.74
    Activations Density 0.010%

    No Known Activations