© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110777
    Prev
    Next
    INDEX
    Explanations

    three.js code snippets

    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
    触发
    -0.88
    skraft
    -0.88
     Fizz
    -0.86
     titans
    -0.85
     Efe
    -0.84
     SNL
    -0.81
     entrées
    -0.80
    ▲
    -0.80
     rois
    -0.79
     Métro
    -0.79
    POSITIVE LOGITS
     Angeles
    0.88
     konz
    0.86
     koment
    0.85
     piaci
    0.84
     idle
    0.84
     religieuses
    0.77
    verbal
    0.77
    ʺ
    0.77
    glut
    0.76
     spise
    0.76
    Activations Density 0.004%

    No Known Activations