© 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. 76779
    Prev
    Next
    INDEX
    Explanations

    a [adjective] group

    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
     members
    -1.21
     individuals
    -1.05
     persons
    -0.98
     füh
    -0.93
     leaders
    -0.89
     líder
    -0.85
    individual
    -0.84
     individual
    -0.84
    Individual
    -0.83
     peers
    -0.81
    POSITIVE LOGITS
     cadre
    1.08
     cohort
    0.94
     pool
    0.93
     EXERCISES
    0.93
     workforce
    0.92
     roster
    0.86
     fidèles
    0.84
     diverse
    0.82
     seura
    0.82
    чайно
    0.81
    Activations Density 0.121%

    No Known Activations