© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78774
    Prev
    Next
    INDEX
    Explanations

    kitchen devices and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mihi
    -0.80
    Océ
    -0.77
    لف
    -0.75
     より
    -0.73
     Perú
    -0.73
     洗濯
    -0.73
    Olymp
    -0.71
     стира
    -0.71
    Portfolio
    -0.70
    Local
    -0.68
    POSITIVE LOGITS
     gadgets
    0.97
    ringo
    0.88
     stainless
    0.86
     gadget
    0.86
     alimentos
    0.85
     blades
    0.83
     BPA
    0.83
    瀝
    0.82
     handheld
    0.81
    hler
    0.81
    Activations Density 0.009%

    No Known Activations