© 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. 40-GEMMASCOPE-2-RES-262K
    7. 465
    Prev
    Next
    INDEX
    Explanations

    limited, ancient, cult, settlement, storage

    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_40_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
     ド
    0.47
     USD
    0.46
     Disney
    0.46
    EUR
    0.45
     ሞ
    0.43
    TECH
    0.43
     可愛
    0.43
    ?
    0.42
     設定
    0.42
    uia
    0.41
    POSITIVE LOGITS
    لي
    0.46
     concatenate
    0.45
    角落
    0.44
    个
    0.44
    集中
    0.42
     einzel
    0.42
    departments
    0.42
     recibido
    0.41
    时代的
    0.41
    福祉
    0.41
    Activations Density 0.000%

    No Known Activations