© 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. 76247
    Prev
    Next
    INDEX
    Explanations

    cryptsoft.com, Cryptodome.PublicKey, Crystal storing

    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
    ̙
    -0.77
     mögen
    -0.74
     σ
    -0.72
    くらいの
    -0.72
     scrapbooking
    -0.72
    ופ
    -0.70
     esist
    -0.70
     entdecken
    -0.69
     virgin
    -0.69
     ن
    -0.69
    POSITIVE LOGITS
     Crystal
    1.02
    Crystal
    0.96
    niveau
    0.80
    kirche
    0.79
     水晶
    0.78
    hafter
    0.77
     crystal
    0.77
    ledning
    0.76
     patrie
    0.75
     Sola
    0.75
    Activations Density 0.031%

    No Known Activations