© 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. 118119
    Prev
    Next
    INDEX
    Explanations

    occupations and roles

    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
    Gön
    -1.84
     matériaux
    -1.73
     vrais
    -1.72
     plafon
    -1.70
     jouets
    -1.68
     échanti
    -1.66
    Interes
    -1.65
     vêtements
    -1.63
     verhind
    -1.61
    Seni
    -1.61
    POSITIVE LOGITS
     all
    2.06
     primarily
    2.06
     only
    1.98
     not
    1.94
     by
    1.92
     Although
    1.91
     which
    1.91
     at
    1.88
     two
    1.88
     both
    1.88
    Activations Density 0.169%

    No Known Activations