© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3852
    Prev
    Next
    INDEX
    Explanations

    depicting landscapes and scenes

    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_16k_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
     Career
    0.45
    写的
    0.42
     rebranded
    0.42
     करियर
    0.42
     Workforce
    0.42
    发言
    0.42
     Skills
    0.42
    婶
    0.42
     Template
    0.41
     acronym
    0.41
    POSITIVE LOGITS
     depicts
    0.77
     depictions
    0.77
     depict
    0.74
     landscapes
    0.73
    ภาพ
    0.72
     depiction
    0.71
     paisajes
    0.69
     paisaje
    0.68
     depicted
    0.68
     зобра
    0.67
    Activations Density 0.227%

    No Known Activations