© 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. 37944
    Prev
    Next
    INDEX
    Explanations

    drinking straws

    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
    ínguez
    -0.80
    auw
    -0.77
     mem
    -0.75
     shackles
    -0.74
     loaves
    -0.74
     suitcase
    -0.73
     soldering
    -0.71
    จับ
    -0.70
    alloc
    -0.70
    pan
    -0.70
    POSITIVE LOGITS
     straw
    3.34
     straws
    3.14
     Straw
    2.75
    straw
    2.56
    Straw
    2.44
     paille
    1.48
     соло
    1.48
     трубо
    1.46
     drinking
    1.31
    Drinking
    1.20
    Activations Density 0.018%

    No Known Activations