© 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. 22-GEMMASCOPE-RES-131K
    4. 39490
    Prev
    Next
    INDEX
    Explanations

    speeding up or delaying actions

    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_22/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
    xdf
    -0.91
    思議
    -0.87
    ਆਂ
    -0.84
    当時は
    -0.84
     Aussehen
    -0.81
     embarazadas
    -0.81
    走り
    -0.81
     dintr
    -0.81
    xfd
    -0.80
     fue
    -0.79
    POSITIVE LOGITS
     faster
    1.15
    ——–
    1.09
    ofus
    1.09
    更快
    1.09
     delay
    1.09
    ———-
    1.07
    ’
    1.05
     quicker
    1.04
    böz
    1.04
     già
    1.02
    Activations Density 0.052%

    No Known Activations