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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39073
    Prev
    Next
    INDEX
    Explanations

    development, growth, expansion

    np_acts-logits-general · gemini-2.5-flash-lite

    development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    普段
    0.54
    த்தனர்
    0.47
    टाला
    0.46
    writeHead
    0.44
    用
    0.43
    鐺
    0.42
    (),
    0.40
    부에
    0.40
     பெற்ற
    0.40
    RNAs
    0.39
    POSITIVE LOGITS
     geliş
    0.58
     розви
    0.49
     desarrollo
    0.47
     meer
    0.44
     koş
    0.44
     yönet
    0.44
    tevõ
    0.44
     sviluppo
    0.43
    entwicklung
    0.43
     ликви
    0.43
    Activations Density 0.000%

    No Known Activations