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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41015
    Prev
    Next
    INDEX
    Explanations

    remote sensing imagery and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allergy
    0.50
    钻
    0.49
    oblins
    0.48
     आजाद
    0.47
     Recruiting
    0.46
    受欢迎
    0.46
     употреб
    0.45
     술
    0.45
     Helpers
    0.45
     જન્મ
    0.45
    POSITIVE LOGITS
     aerial
    0.89
     satellite
    0.80
     vegetation
    0.78
     imagery
    0.77
     NDVI
    0.74
    Aerial
    0.71
    aerial
    0.69
     reflectance
    0.68
    imagery
    0.67
     land
    0.66
    Activations Density 0.067%

    No Known Activations