© 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. 91206
    Prev
    Next
    INDEX
    Explanations

    platform architecture classification

    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
    unusual
    -0.82
    MENTE
    -0.81
     와
    -0.80
     każdym
    -0.80
     poziomie
    -0.78
    Topics
    -0.78
    nha
    -0.78
     slou
    -0.77
    $};
    -0.77
    aree
    -0.77
    POSITIVE LOGITS
     choice
    1.59
     preference
    1.38
     choices
    1.30
     selection
    1.09
     preferences
    1.07
     pilihan
    1.04
     classification
    1.04
     category
    1.03
     designation
    1.02
     affiliation
    1.02
    Activations Density 0.177%

    No Known Activations