© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 109072
    Prev
    Next
    INDEX
    Explanations

    technical concepts and specific entities

    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
    اری
    0.48
    ç
    0.48
    Über
    0.48
    ﺎ
    0.48
    Airbnb
    0.46
    ও
    0.45
    Ru
    0.44
    یا
    0.43
    тери
    0.43
    Hiro
    0.42
    POSITIVE LOGITS
     wells
    0.45
     HAVE
    0.45
     ingot
    0.44
     annoyed
    0.43
     bottles
    0.43
     vials
    0.43
     cranes
    0.43
     innovators
    0.42
    পন্ন
    0.42
     mustn
    0.42
    Activations Density 0.002%

    No Known Activations