© 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. 91343
    Prev
    Next
    INDEX
    Explanations

    moon glow or light

    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
    zuführen
    -0.84
    0
    -0.82
     Gewähr
    -0.80
     trailed
    -0.79
    Deadpool
    -0.79
     bemerken
    -0.77
     Singles
    -0.75
     menilai
    -0.75
     armée
    -0.75
     consentimiento
    -0.75
    POSITIVE LOGITS
    beam
    1.28
     moon
    1.27
    🌙
    1.23
     Moon
    1.17
    moon
    1.14
     phases
    1.13
    Moon
    1.05
    lighting
    1.05
    beams
    0.99
    lit
    0.98
    Activations Density 0.011%

    No Known Activations