© 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. 10173
    Prev
    Next
    INDEX
    Explanations

    don't wait

    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
    負
    1.67
    اؤ
    1.67
     القرار
    1.58
    Unlocked
    1.56
    owlapi
    1.55
    ަނ
    1.53
    زور
    1.53
    暾
    1.53
    يت
    1.52
    Pause
    1.52
    POSITIVE LOGITS
    度的
    1.61
     bò
    1.49
     community
    1.41
     आदित्य
    1.37
     mùi
    1.36
     kinh
    1.33
     surgical
    1.29
     kỳ
    1.27
     shoes
    1.26
     gioi
    1.25
    Activations Density 0.009%

    No Known Activations