© 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. 93759
    Prev
    Next
    INDEX
    Explanations

    I followed by actions

    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
    相信
    -1.06
     είναι
    -1.06
     έχουν
    -1.05
     estadounid
    -1.01
    США
    -0.99
    wki
    -0.95
     medan
    -0.92
    诡异
    -0.92
     telah
    -0.91
    Ἡ
    -0.91
    POSITIVE LOGITS
     first
    2.30
     started
    2.05
     was
    1.87
     heard
    1.73
     see
    1.61
     say
    1.60
     saw
    1.55
     began
    1.55
     look
    1.54
     talk
    1.54
    Activations Density 0.044%

    No Known Activations