© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4159
    Prev
    Next
    INDEX
    Explanations

    Fire followed by tech product

    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
     projet
    -0.81
    MULT
    -0.80
    tanaman
    -0.77
    页面存档备份
    -0.73
     забы
    -0.73
     Termine
    -0.73
    ieť
    -0.72
     ООО
    -0.72
     momenti
    -0.71
    logOut
    -0.70
    POSITIVE LOGITS
     TV
    1.38
    TV
    1.22
    tv
    1.04
     stick
    0.92
     tv
    0.91
     Fires
    0.85
     fires
    0.81
     Stick
    0.81
     fire
    0.74
     TVs
    0.74
    Activations Density 0.035%

    No Known Activations