© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12650
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives for size, age, and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    ي
    2.06
    y
    1.99
    s
    1.95
    ת
    1.88
    йки
    1.88
    я
    1.83
    ی
    1.79
    й
    1.76
    ాన్ని
    1.61
    ことができます
    1.60
    POSITIVE LOGITS
    Than
    1.47
    ুপ
    1.39
    𝙧
    1.26
     than
    1.24
    ޝ
    1.23
     t
    1.20
    than
    1.18
     THAN
    1.14
    δία
    1.14
    즘
    1.12
    Activations Density 0.465%

    No Known Activations