© 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. 112849
    Prev
    Next
    INDEX
    Explanations

    legal malpractice

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

    danger and harm

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Predict
    0.46
    ן
    0.46
    和社会
    0.46
     Create
    0.45
     Produce
    0.45
     italiana
    0.45
     They
    0.45
     Music
    0.45
    ف
    0.45
    س
    0.44
    POSITIVE LOGITS
     секрета
    0.49
    पद
    0.48
     оско
    0.47
     Фурга
    0.46
    錠
    0.45
     назнача
    0.45
     پہ
    0.44
     пост
    0.44
     ގ
    0.44
     blushed
    0.44
    Activations Density 0.001%

    No Known Activations