© 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. 38579
    Prev
    Next
    INDEX
    Explanations

    epitaxial growth

    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
    вии
    -0.82
    haustible
    -0.76
    menes
    -0.76
    Wanneer
    -0.74
     Texans
    -0.74
    uksen
    -0.73
    CAA
    -0.73
    guri
    -0.73
    ダー
    -0.72
     głoś
    -0.72
    POSITIVE LOGITS
     epit
    1.26
     overgrown
    0.96
     growth
    0.95
     lattice
    0.94
     MBE
    0.92
     MOC
    0.91
     Epit
    0.88
    lattice
    0.87
     mis
    0.86
     strain
    0.83
    Activations Density 0.070%

    No Known Activations