© 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. 10202
    Prev
    Next
    INDEX
    Explanations

    alcohol use and abuse

    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
    ណ្ឌ
    2.05
    ﻥ
    2.04
     declarations
    1.82
    ਡੀ
    1.81
     ?>
    1.80
    𝐧
    1.79
    म
    1.77
     surcharge
    1.75
    、『
    1.74
    𝒍
    1.74
    POSITIVE LOGITS
    nya
    2.60
    了
    2.16
    shire
    2.15
    substr
    2.14
    sia
    2.05
    sg
    1.95
    sis
    1.91
    ியுள்ள
    1.82
    sez
    1.79
    sf
    1.76
    Activations Density 0.097%

    No Known Activations