© 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. 59105
    Prev
    Next
    INDEX
    Explanations

    coast guard and coast to coast

    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
     Pristup
    -0.90
     walls
    -0.85
     Schülerinnen
    -0.82
     Christendom
    -0.81
     Aliexpress
    -0.81
    স্
    -0.80
     motocross
    -0.79
     ın
    -0.79
    CTOR
    -0.79
     miniatur
    -0.78
    POSITIVE LOGITS
    line
    1.57
     Coast
    1.49
    coast
    1.27
     line
    1.25
     coast
    1.12
    ine
    1.12
     guard
    1.11
    guard
    1.11
     Guard
    1.08
    Coast
    1.05
    Activations Density 0.007%

    No Known Activations