© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79155
    Prev
    Next
    INDEX
    Explanations

    communication and collaboration

    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
     communications
    -2.13
     communication
    -2.02
    communication
    -1.98
     Communications
    -1.97
    communications
    -1.87
    Communications
    -1.86
    Communication
    -1.85
     Communication
    -1.77
    COMMUNIC
    -1.74
     communicate
    -1.66
    POSITIVE LOGITS
     collaboration
    0.82
     computation
    0.81
     }}\
    0.77
     Güter
    0.77
    +="
    0.71
     listening
    0.71
    рного
    0.71
     Computing
    0.69
     hearing
    0.69
     transportation
    0.69
    Activations Density 0.034%

    No Known Activations