© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1770
    Prev
    Next
    INDEX
    Explanations

    costs and fees

    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_17_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
     потеря
    0.87
    킵
    0.83
     उतर
    0.83
    وٹ
    0.82
    حاء
    0.79
    どんど
    0.77
     stamina
    0.77
    ترین
    0.77
     Doctorate
    0.76
    エース
    0.76
    POSITIVE LOGITS
     khỏi
    1.09
     altogether
    1.02
    桎
    0.97
     کامل
    0.92
     proposito
    0.89
    聒
    0.87
    一切
    0.87
    ৩২
    0.87
     언급
    0.87
    ৩৯
    0.86
    Activations Density 0.230%

    No Known Activations