© 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. 65787
    Prev
    Next
    INDEX
    Explanations

    members of organizations

    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
     mengam
    -0.92
     melindungi
    -0.90
     menangani
    -0.90
     mengumpulkan
    -0.86
    สิ่ง
    -0.83
     memperbaiki
    -0.81
     mengatasi
    -0.81
     menyiapkan
    -0.79
     mengembangkan
    -0.79
     Personen
    -0.79
    POSITIVE LOGITS
     member
    6.22
     members
    5.97
     membership
    4.84
    member
    4.69
     Member
    4.59
     Members
    4.53
    members
    4.47
    Members
    4.28
    Member
    4.25
    MEMBER
    4.06
    Activations Density 0.166%

    No Known Activations