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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 355
    Prev
    Next
    INDEX
    Explanations

    places and their historical/natural beauty

    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
    ኅ
    1.00
     steels
    0.96
     ด่า
    0.93
     dígitos
    0.91
     mRNAs
    0.91
    ร่าง
    0.90
     PREFIX
    0.88
    膛
    0.88
    olverine
    0.88
     தலைமை
    0.88
    POSITIVE LOGITS
     attractions
    2.06
     sightseeing
    2.05
     tourist
    2.00
     touristic
    1.97
     beaches
    1.91
     tourism
    1.85
     waterfalls
    1.82
     관광
    1.79
     nightlife
    1.78
     Attractions
    1.78
    Activations Density 4.061%

    No Known Activations