© 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. 6724
    Prev
    Next
    INDEX
    Explanations

    docstrings

    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
    ಹಾರ
    1.06
    }`))
    1.02
    বঙ্গের
    0.99
    }`));
    0.98
    뜩
    0.98
     presidente
    0.93
    ത്തുന്ന
    0.92
    _{(\
    0.90
     গ্রামের
    0.89
     dilat
    0.89
    POSITIVE LOGITS
    ótica
    1.18
    ерт
    1.15
    ocup
    1.13
    ocar
    1.11
    ocop
    1.06
    otham
    1.05
    redo
    1.02
    lox
    1.00
    ottom
    0.99
    ERTS
    0.98
    Activations Density 0.029%

    No Known Activations