© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189868
    Prev
    Next
    INDEX
    Explanations

    sun movement and times

    np_acts-logits-general · gemini-2.5-flash-lite

    sunlight and times of day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    悸
    0.39
    ickness
    0.38
    厷
    0.38
    ตอบ
    0.38
    กรม
    0.38
    oloji
    0.37
    ℑ
    0.37
    טה
    0.37
     الرحمن
    0.37
    ضب
    0.37
    POSITIVE LOGITS
     sun
    0.61
     sunset
    0.60
     sunrise
    0.55
     winter
    0.52
     evening
    0.49
     shadows
    0.49
    sunset
    0.49
     sunsets
    0.49
     Winter
    0.48
     sunlight
    0.48
    Activations Density 0.058%

    No Known Activations