© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6883
    Prev
    Next
    INDEX
    Explanations

    even more

    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_22_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
    投放
    1.25
    Avatar
    1.01
     pedro
    0.98
     Amman
    0.96
     মেয়র
    0.96
    系統
    0.95
    vout
    0.95
     낙
    0.94
     Adonis
    0.94
    长安
    0.93
    POSITIVE LOGITS
     histone
    1.09
     chromatin
    0.97
     DNA
    0.95
    DNA
    0.95
    绷
    0.94
    winding
    0.91
     deacetyl
    0.85
     compacted
    0.83
     coils
    0.82
    螺旋
    0.82
    Activations Density 0.062%

    No Known Activations