© 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. 10363
    Prev
    Next
    INDEX
    Explanations

    city names and descriptors

    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
    entin
    0.89
     odv
    0.88
     uner
    0.88
    ㈜
    0.87
     Madre
    0.83
    ritten
    0.82
    brano
    0.82
     RAC
    0.82
    라이언
    0.82
    ρί
    0.82
    POSITIVE LOGITS
    ですし
    1.05
     ہتھی
    1.05
    naires
    0.98
    ás
    0.96
    ूक
    0.95
     corpora
    0.93
    呢
    0.93
    никами
    0.92
    arios
    0.91
    してくれる
    0.90
    Activations Density 0.005%

    No Known Activations