© 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. 38272
    Prev
    Next
    INDEX
    Explanations

    arriving at, upon an

    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
     and
    -1.95
     first
    -1.73
     gives
    -1.38
     for
    -1.36
     from
    -1.32
     puts
    -1.31
     starts
    -1.31
     considerable
    -1.21
     while
    -1.21
     to
    -1.21
    POSITIVE LOGITS
     ジップ
    1.68
    aning
    1.54
    𝒙
    1.53
     каком
    1.46
    鵙
    1.45
    couz
    1.44
    
    1.42
    carus
    1.40
     .(
    1.38
     שאי
    1.38
    Activations Density 0.062%

    No Known Activations