© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2939
    Prev
    Next
    INDEX
    Explanations

    harmful behavior or acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     بهبود
    2.00
    คุณภาพ
    1.95
    优质
    1.94
    ilmiştir
    1.90
    columnwidth
    1.89
     painstakingly
    1.84
    ibank
    1.83
     pivotal
    1.81
    巩
    1.79
    ed
    1.79
    POSITIVE LOGITS
    URLException
    2.18
    NESS
    2.06
     doings
    1.81
    妄
    1.78
    ties
    1.77
     xạ
    1.75
    kita
    1.63
    andering
    1.61
    tics
    1.61
    installer
    1.60
    Activations Density 0.438%

    No Known Activations