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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 14390
    Prev
    Next
    INDEX
    Explanations

    when followed by a pronoun

    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_16_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
    ما
    0.66
    a
    0.51
    u
    0.48
    </h4>
    0.48
    </h2>
    0.47
    </h1>
    0.47
     It
    0.47
    ف
    0.47
    0.46
    to
    0.46
    POSITIVE LOGITS
    ﻲ
    0.57
    ﻼ
    0.51
    ИТ
    0.50
    에요
    0.50
    Т
    0.50
    ).
    0.50
    ల్‌
    0.49
    ."
    0.49
    ”
    0.48
    ﻂ
    0.48
    Activations Density 0.019%

    No Known Activations