© 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. 99882
    Prev
    Next
    INDEX
    Explanations

    architectures, cultural, brain, data, annual

    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
     Tala
    0.45
    鸠
    0.43
    وال
    0.42
     heuristics
    0.42
     lighter
    0.41
     እንኳን
    0.41
     aulas
    0.41
    howto
    0.41
     stopwords
    0.41
     подс
    0.41
    POSITIVE LOGITS
    inqui
    0.39
    ificent
    0.38
     ユ
    0.38
    ティブ
    0.38
     nuestro
    0.37
    ments
    0.36
     επιχει
    0.36
     собственно
    0.36
    ડો
    0.35
     लागले
    0.35
    Activations Density 0.001%

    No Known Activations