© 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-65K
    7. 56158
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hObject
    0.46
    oski
    0.41
    蜚
    0.40
    oradi
    0.39
    wür
    0.39
    rijke
    0.39
    voerd
    0.39
    塊
    0.39
    zeichnis
    0.38
     ہوں
    0.38
    POSITIVE LOGITS
     picks
    0.43
     bottom
    0.42
    Norm
    0.42
    モノ
    0.41
     Heather
    0.39
     suit
    0.38
     cartel
    0.38
     favors
    0.37
     пола
    0.37
     jaw
    0.36
    Activations Density 0.001%

    No Known Activations