© 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. 107823
    Prev
    Next
    INDEX
    Explanations

    Laughlin or laughing words

    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
    𝗽
    -0.75
    ExtendWith
    -0.74
     Priory
    -0.73
     Bege
    -0.73
    囍
    -0.71
     아이
    -0.71
    celess
    -0.69
    colare
    -0.68
    innerWidth
    -0.67
     Rohan
    -0.67
    POSITIVE LOGITS
    urus
    0.82
    lin
    0.82
     amiss
    0.77
     spake
    0.75
    Closing
    0.75
    ciclopedia
    0.73
     аса
    0.72
     Riot
    0.71
     upro
    0.70
     riot
    0.70
    Activations Density 0.026%

    No Known Activations