© 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. 56874
    Prev
    Next
    INDEX
    Explanations

    user in context

    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
    凖
    0.46
    哥
    0.46
     बंद
    0.45
    Autonomous
    0.45
    綣
    0.45
    اي
    0.44
    Closed
    0.44
    ပ
    0.44
    몇
    0.43
    崭
    0.43
    POSITIVE LOGITS
     city
    0.47
     cities
    0.47
    water
    0.46
    by
    0.44
     water
    0.41
     street
    0.41
     worksheet
    0.41
     towns
    0.40
    s
    0.40
    housing
    0.39
    Activations Density 0.007%

    No Known Activations