© 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. 130266
    Prev
    Next
    INDEX
    Explanations

    certain words following "ambition" or "dragon"

    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
    ᅱ
    0.43
    spreadsheet
    0.42
    otheli
    0.42
     spreadsheet
    0.42
    ायला
    0.42
    保護
    0.41
     ঘোষণ
    0.40
     захи
    0.40
     ناخد
    0.40
     Spreadsheet
    0.39
    POSITIVE LOGITS
     elección
    0.48
     ​​
    0.41
     seçim
    0.39
     choice
    0.39
     chose
    0.39
     motivación
    0.38
     Moscow
    0.38
     phản
    0.38
     Toy
    0.38
    )|\
    0.37
    Activations Density 0.002%

    No Known Activations