© 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. 22-GEMMASCOPE-RES-131K
    4. 13181
    Prev
    Next
    INDEX
    Explanations

    descriptive separators and content

    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_22/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
    ṇa
    -1.02
    ãy
    -0.93
     surrender
    -0.85
    kussion
    -0.85
    loroethene
    -0.82
    니까
    -0.82
    <eos>
    -0.78
     канали
    -0.78
    ticas
    -0.76
    testng
    -0.75
    POSITIVE LOGITS
     SAMPLE
    0.80
    booth
    0.80
     this
    0.79
    mment
    0.79
    lede
    0.77
     iu
    0.77
     gedachten
    0.76
    .$_
    0.76
    например
    0.75
     vroe
    0.73
    Activations Density 0.043%

    No Known Activations