© 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. 17431
    Prev
    Next
    INDEX
    Explanations

    X, O, key, uneven

    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
     did
    0.48
     acab
    0.46
    在
    0.44
     stopp
    0.44
    看看
    0.43
    Aire
    0.43
     potencialmente
    0.42
    ↵
    0.42
    启
    0.42
    TC
    0.41
    POSITIVE LOGITS
    ┣
    0.55
     มั้ย
    0.48
    stargo
    0.46
    uw
    0.46
    سازی
    0.45
    ստ
    0.44
    সন্
    0.43
    selfobj
    0.43
    reflectionMap
    0.43
    ptir
    0.43
    Activations Density 0.001%

    No Known Activations