© 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. 84102
    Prev
    Next
    INDEX
    Explanations

    coin collecting

    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
     мес
    -0.83
    0
    -0.83
     bobs
    -0.83
     Brethren
    -0.81
     دوستان
    -0.81
     Proces
    -0.80
     Penang
    -0.77
     Beyoncé
    -0.77
     Respiratory
    -0.77
     too
    -0.75
    POSITIVE LOGITS
     coin
    1.39
     Coin
    1.34
    Coin
    1.23
     toss
    1.20
    coin
    1.12
    𝙻
    1.05
    DEX
    1.03
    laundry
    1.00
    XICO
    0.98
     laundry
    0.97
    Activations Density 0.006%

    No Known Activations