© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13418
    Prev
    Next
    INDEX
    Explanations

    negative stereotypes and exploitation

    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_13_width_16k_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
    ანა
    0.93
    )
    0.89
    &
    0.89
    lom
    0.85
    tung
    0.82
    GREAT
    0.79
    ～
    0.79
    〜
    0.78
    due
    0.78
    )~
    0.78
    POSITIVE LOGITS
     misalnya
    1.90
     beispielsweise
    1.79
     például
    1.69
     například
    1.68
     কিংবা
    1.68
     bijvoorbeeld
    1.67
     ebenso
    1.62
    或是
    1.61
     esimerkiksi
    1.58
    或者是
    1.57
    Activations Density 0.236%

    No Known Activations