© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8110
    Prev
    Next
    INDEX
    Explanations

    countries and cities

    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
     what
    1.98
     this
    1.96
     some
    1.88
     a
    1.85
     our
    1.79
     it
    1.75
     你
    1.75
     quasi
    1.69
     an
    1.69
     THIS
    1.67
    POSITIVE LOGITS
    etc
    2.05
    Otros
    2.01
    Royal
    1.87
    Apollo
    1.87
    Kah
    1.87
    Gambar
    1.87
    إ
    1.86
    EPA
    1.86
    Dong
    1.85
    Bor
    1.83
    Activations Density 0.100%

    No Known Activations