© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3922
    Prev
    Next
    INDEX
    Explanations

    subtle control and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ashi
    1.51
    Attention
    1.46
     visão
    1.44
     styr
    1.41
     gás
    1.41
    <strong>
    1.37
    United
    1.37
    Res
    1.36
     tarik
    1.35
     view
    1.35
    POSITIVE LOGITS
     wrongdoing
    2.67
     punishable
    2.56
     sinned
    2.54
     felonies
    2.54
     misdemean
    2.54
     perpetrated
    2.46
     sinful
    2.46
     misconduct
    2.45
    죄
    2.43
     جرم
    2.39
    Activations Density 0.217%

    No Known Activations