© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38293
    Prev
    Next
    INDEX
    Explanations

    access from anywhere

    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
     לת
    -0.91
    ごとに
    -0.88
    inheritdoc
    -0.85
     Мексичка
    -0.84
    "]));
    -0.82
    ègre
    -0.81
    中医
    -0.79
     유
    -0.77
     to
    -0.76
    lavi
    -0.75
    POSITIVE LOGITS
     anywhere
    2.70
     wherever
    2.67
    anywhere
    2.03
     from
    2.02
     Anywhere
    1.94
     remotely
    1.84
    Wherever
    1.83
     Wherever
    1.78
    Anywhere
    1.77
     anytime
    1.70
    Activations Density 0.065%

    No Known Activations