© 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. 10-GEMMASCOPE-RES-131K
    7. 111663
    Prev
    Next
    INDEX
    Explanations

    days of the week or dates

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on terminology describing VEX robotics game elements and robot sensors (e.g. picking up balls/barrels, cylinders/goals, ultrasonic/sonar/bump sensors, encoders).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     ferien
    -1.84
    暧
    -1.50
    ÈNE
    -1.45
     ideen
    -1.37
    ској
    -1.37
    抵达
    -1.35
    挑选
    -1.34
     prosi
    -1.31
     domestiques
    -1.30
     flamme
    -1.30
    POSITIVE LOGITS
     Friday
    1.64
     Thursday
    1.56
     Saturday
    1.50
    愜
    1.48
    .*;
    1.47
     gewann
    1.46
     Erzb
    1.45
     More
    1.45
     stellte
    1.45
     Wednesday
    1.43
    Activations Density 0.005%

    No Known Activations