© 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. 2123
    Prev
    Next
    INDEX
    Explanations

    computer software and platforms

    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
     socks
    1.04
     Coney
    0.93
    socks
    0.92
     sillons
    0.91
    ฬ
    0.90
    дени
    0.90
    ophobic
    0.89
    旃
    0.88
     bronchi
    0.86
     biển
    0.86
    POSITIVE LOGITS
     software
    2.57
     softwares
    2.45
     Adobe
    2.35
    software
    2.34
    软件
    2.32
     Software
    2.31
     AutoCAD
    2.28
     Photoshop
    2.27
     Microsoft
    2.26
    Software
    2.19
    Activations Density 1.323%

    No Known Activations