© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2388
    Prev
    Next
    INDEX
    Explanations

    tokenization and suffixes like -ization

    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_all/layer_41_width_262k_l0_big
    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
    زاء
    0.47
     तरल
    0.47
    ITTLE
    0.47
    ᓲ
    0.44
     नाइट्रेट
    0.43
    ের
    0.42
    エネルギー
    0.42
     inoculum
    0.42
    मूलन
    0.41
    テナンス
    0.41
    POSITIVE LOGITS
    ization
    0.95
    ized
    0.93
    izing
    0.83
    化
    0.83
    isasi
    0.81
    化的
    0.77
    isation
    0.76
    isierung
    0.76
    ización
    0.72
    izacja
    0.72
    Activations Density 0.004%

    No Known Activations