© 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. 1037
    Prev
    Next
    INDEX
    Explanations

    software, tools, and frameworks

    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
    HttpSecurity
    0.94
    뇽
    0.89
    Stef
    0.85
     मुकेश
    0.84
    rugada
    0.83
     martyrs
    0.81
     Akash
    0.81
    襬
    0.80
    리스마
    0.80
    OrderBy
    0.79
    POSITIVE LOGITS
     software
    2.80
     tool
    2.75
    软件
    2.64
    software
    2.47
     softwares
    2.42
    軟件
    2.36
     tools
    2.35
     Tool
    2.35
     logiciel
    2.34
    tool
    2.29
    Activations Density 2.359%

    No Known Activations