© 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. 77564
    Prev
    Next
    INDEX
    Explanations

    natural 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
    ⠪
    -0.83
     fb
    -0.82
    サキ
    -0.81
     sfera
    -0.79
    auté
    -0.77
     estilos
    -0.76
    cooldown
    -0.75
    σθαι
    -0.74
     stelt
    -0.73
    
    -0.73
    POSITIVE LOGITS
     sunlight
    2.11
     light
    1.97
     bright
    1.93
     natural
    1.86
     daylight
    1.73
     brightness
    1.70
    Bright
    1.55
    bright
    1.52
     sunshine
    1.52
     brightening
    1.47
    Activations Density 0.017%

    No Known Activations