© 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. 119092
    Prev
    Next
    INDEX
    Explanations

    for purposes

    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
    -1.98
     penchant
    -0.97
     étant
    -0.94
    为大家
    -0.93
    事が
    -0.91
     being
    -0.91
     erneut
    -0.90
     vying
    -0.90
     erfolgt
    -0.89
     relação
    -0.88
    POSITIVE LOGITS
     purposes
    4.88
    purposes
    3.47
     purpose
    3.05
     Purposes
    2.80
     sake
    2.59
     reasons
    2.05
    purpose
    1.83
     PURPOSE
    1.77
     propósitos
    1.70
    Purpose
    1.68
    Activations Density 0.191%

    No Known Activations