© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119786
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions or situations

    np_acts-logits-general · gemini-2.5-flash-lite

    role play scenario: student learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ”
    0.52
     Electrical
    0.50
     originate
    0.48
     weddings
    0.48
     exciting
    0.47
     Acceler
    0.47
     NASDAQ
    0.46
     STEM
    0.45
     endangered
    0.45
     STEAM
    0.45
    POSITIVE LOGITS
    法规
    0.49
     പറഞ്ഞു
    0.49
    法令
    0.49
    贬
    0.48
    谴
    0.48
     подпис
    0.46
    作成
    0.46
     поведение
    0.46
     സമൂ
    0.46
     سزا
    0.46
    Activations Density 0.000%

    No Known Activations