© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116295
    Prev
    Next
    INDEX
    Explanations

    family and faculty members

    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
     mendorong
    -1.03
     memperhatikan
    -1.02
     melindungi
    -0.99
     mengirimkan
    -0.96
     mengumpulkan
    -0.95
     mendengarkan
    -0.92
     memimpin
    -0.87
     menyiapkan
    -0.87
     berkomunikasi
    -0.86
     menangani
    -0.85
    POSITIVE LOGITS
     members
    4.81
     member
    4.22
    members
    3.13
    Members
    2.94
     miembros
    2.86
    member
    2.86
    成员
    2.72
     MEMBERS
    2.72
     Members
    2.58
     membres
    2.52
    Activations Density 0.036%

    No Known Activations