© 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. 21367
    Prev
    Next
    INDEX
    Explanations

    collecting things, ideas, or philosophies

    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
    㖅
    0.45
     जानने
    0.43
    ້າງ
    0.42
    㜿
    0.42
    ક્ર
    0.42
    acks
    0.41
    埓
    0.41
     तळ
    0.40
    colorbar
    0.39
     భాగంగా
    0.39
    POSITIVE LOGITS
     Collect
    0.83
     collect
    0.71
     Collector
    0.70
     COLLECT
    0.68
     collecting
    0.67
    collect
    0.66
     collector
    0.64
     Collectors
    0.64
     collectors
    0.64
     коллек
    0.62
    Activations Density 0.009%

    No Known Activations