© 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. 8083
    Prev
    Next
    INDEX
    Explanations

    names of places and cultures

    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
     幅
    0.86
    മം
    0.86
     λέ
    0.85
     impl
    0.85
    மம்
    0.84
     कर्म
    0.83
     అన్నారు
    0.83
     générale
    0.82
     Greece
    0.82
    屁
    0.82
    POSITIVE LOGITS
    asian
    1.71
    ussian
    1.69
    onesian
    1.69
    amese
    1.66
    anese
    1.64
    assian
    1.64
    aiian
    1.62
    anian
    1.58
    uvian
    1.58
    amian
    1.57
    Activations Density 0.275%

    No Known Activations