© 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. 6643
    Prev
    Next
    INDEX
    Explanations

    youtube video links

    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
    Negative Logits
    /**
    1.05
    MODE
    1.04
     mâle
    1.04
     தாக்கு
    1.02
     आतंकी
    1.01
     ćel
    1.00
     psih
    0.99
     kháng
    0.98
     sử
    0.98
     मलिक
    0.98
    POSITIVE LOGITS
    rt
    0.83
    rena
    0.77
    arget
    0.72
    潭
    0.71
    akot
    0.71
    oret
    0.71
    रेन
    0.71
    ours
    0.70
    ething
    0.70
    ungsseite
    0.69
    Activations Density 0.006%

    No Known Activations