© 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. 83448
    Prev
    Next
    INDEX
    Explanations

    company names or locations

    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
    哆
    -1.05
    是一款
    -0.98
    Stanford
    -0.87
     Cosby
    -0.86
     Vauxhall
    -0.85
    APORE
    -0.84
     `"
    -0.84
     รุ่น
    -0.83
    ontale
    -0.82
    春季
    -0.82
    POSITIVE LOGITS
     software
    1.02
     Advanced
    1.01
     глоба
    0.93
    Origen
    0.93
     Global
    0.92
     Env
    0.89
     Inte
    0.88
     Integer
    0.88
     global
    0.88
     Amer
    0.85
    Activations Density 0.082%

    No Known Activations