© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11316
    Prev
    Next
    INDEX
    Explanations

    crystal followed by a noun

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

    cryptocurrency and cryptography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    に着
    0.42
    玝
    0.38
     Motions
    0.37
    ☸
    0.37
    éraire
    0.36
     muted
    0.36
    щей
    0.36
    等が
    0.35
    架
    0.35
     Boley
    0.35
    POSITIVE LOGITS
     кри
    0.85
    crystal
    0.72
     crystal
    0.70
     krist
    0.70
     crystall
    0.69
     cristal
    0.69
    crystall
    0.68
     Crystal
    0.68
     кристал
    0.68
     Krist
    0.67
    Activations Density 0.067%

    No Known Activations