© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48590
    Prev
    Next
    INDEX
    Explanations

    programming constructs and common words

    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
     trie
    -0.94
    Véxase
    -0.93
    Sophomore
    -0.91
    unico
    -0.88
     ooit
    -0.88
     套装
    -0.86
     werkt
    -0.86
    Magical
    -0.84
     enviados
    -0.84
    BEFORE
    -0.84
    POSITIVE LOGITS
    ness
    0.88
    ﹄
    0.88
    を入
    0.87
    说法
    0.85
    บาย
    0.84
    eger
    0.81
    ąpi
    0.80
     Metropolitan
    0.79
    ヅ
    0.78
    that
    0.77
    Activations Density 0.126%

    No Known Activations