© 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. 27879
    Prev
    Next
    INDEX
    Explanations

    non-english words and specific concepts

    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
     coalgebra
    0.48
     elves
    0.47
     translations
    0.46
     FontFamily
    0.46
    aksi
    0.46
     maids
    0.46
     Ties
    0.44
    🚥
    0.44
    ជាប់
    0.43
    जेक्शन
    0.42
    POSITIVE LOGITS
     autént
    0.49
    нер
    0.48
    ндә
    0.47
    日本の
    0.47
    本の
    0.47
    anche
    0.46
    QTTR
    0.45
    ڈ
    0.45
    ()){
    0.45
    人
    0.44
    Activations Density 0.000%

    No Known Activations