© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65161
    Prev
    Next
    INDEX
    Explanations

    specific phrases and contexts

    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
     xrange
    -0.90
     didnt
    -0.82
     😌
    -0.81
    っていない
    -0.81
     😩
    -0.80
     extravagant
    -0.78
    DataStore
    -0.77
    ਗ
    -0.77
    されていない
    -0.77
     😏
    -0.77
    POSITIVE LOGITS
     Covid
    1.04
     androidx
    0.98
    constexpr
    0.96
    Covid
    0.94
    ​​​​​​​
    0.92
     altijd
    0.85
     цифро
    0.84
    🌡
    0.84
    γρα
    0.84
     Container
    0.84
    Activations Density 0.001%

    No Known Activations