© 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-262K
    7. 99829
    Prev
    Next
    INDEX
    Explanations

    sometimes or typically with a description

    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
    મ
    0.53
     ಪೊಲೀಸ
    0.45
    р
    0.45
     barter
    0.45
    collectibles
    0.44
    altezza
    0.43
    router
    0.43
     imate
    0.43
    ר
    0.43
    的产品
    0.42
    POSITIVE LOGITS
     pathogens
    0.48
    itemName
    0.43
     Lankan
    0.42
    \\.
    0.41
    亗
    0.41
     mayors
    0.41
    人之
    0.41
    :
    0.40
     هدف
    0.40
     shì
    0.40
    Activations Density 0.001%

    No Known Activations