© 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. 115457
    Prev
    Next
    INDEX
    Explanations

    professions 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
     for
    -1.35
     location
    -1.34
    re
    -1.31
     being
    -1.30
    ta
    -1.30
    el
    -1.27
    co
    -1.23
    ea
    -1.22
    ve
    -1.18
     different
    -1.18
    POSITIVE LOGITS
     who
    3.95
     and
    2.72
     whom
    1.81
    hips
    1.70
     الذين
    1.70
     kteří
    1.67
     ktorí
    1.56
    whom
    1.49
     którzy
    1.45
     whoſe
    1.45
    Activations Density 0.200%

    No Known Activations