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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10957
    Prev
    Next
    INDEX
    Explanations

    Sustainability, technical, multilingual

    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
    RuntimeException
    1.02
    =":
    1.01
     সক্রিয়
    1.00
    リティ
    0.98
    rary
    0.97
    िल्या
    0.97
    యో
    0.94
    惮
    0.94
    ideos
    0.93
    arge
    0.91
    POSITIVE LOGITS
     Qin
    0.96
     Cous
    0.91
     Pierce
    0.91
     CuSO
    0.91
     ку
    0.90
     Kob
    0.90
     <=
    0.89
     Koh
    0.89
     Julius
    0.86
     Reuben
    0.85
    Activations Density 0.001%

    No Known Activations