© 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. 76186
    Prev
    Next
    INDEX
    Explanations

    defining considerations

    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
     được
    -1.03
    婢
    -0.90
    ensibility
    -0.89
     Julie
    -0.89
     vegetarian
    -0.84
    pompa
    -0.81
     Suggest
    -0.80
    ynie
    -0.80
     beijo
    -0.79
     obten
    -0.79
    POSITIVE LOGITS
     consider
    1.88
    consider
    1.44
    Consider
    1.34
     considers
    1.31
     betrachten
    1.20
     treat
    1.15
     replace
    1.14
     regard
    1.13
     рассматри
    1.13
     betrachtet
    1.09
    Activations Density 0.108%

    No Known Activations