© 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. 82621
    Prev
    Next
    INDEX
    Explanations

    true, false, 1, or 0

    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
    nine
    -0.92
     ۱۳۹
    -0.89
    twelve
    -0.87
     forty
    -0.85
     ۱۴۰۰
    -0.84
     thirty
    -0.84
     ۱۳۸
    -0.84
    6
    -0.81
    ToReturn
    -0.81
     twenty
    -0.80
    POSITIVE LOGITS
     ۱
    1.82
    1
    1.77
     yes
    1.48
     one
    1.44
    ۱
    1.33
     Yes
    1.32
     YES
    1.30
    Yes
    1.24
     true
    1.23
     TRUE
    1.22
    Activations Density 0.067%

    No Known Activations