© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108123
    Prev
    Next
    INDEX
    Explanations

    night sky and moon

    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
    Lunch
    -1.76
     sunny
    -1.76
     lunch
    -1.73
     Lunch
    -1.60
     lunchtime
    -1.59
    lunch
    -1.51
     afternoon
    -1.50
     sun
    -1.43
    afternoon
    -1.38
     sunshine
    -1.36
    POSITIVE LOGITS
     moonlight
    2.66
     night
    2.30
     nocturnal
    2.28
     moon
    2.11
     Night
    2.00
     darkness
    1.94
     midnight
    1.92
     Moonlight
    1.89
     nighttime
    1.88
    Moonlight
    1.88
    Activations Density 0.070%

    No Known Activations