© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 559
    Prev
    Next
    INDEX
    Explanations

    that/who introducing descriptive clauses

    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
    ä
    0.44
    soever
    0.42
    وم
    0.40
    are
    0.40
    ريكية
    0.38
    لية
    0.37
     obstante
    0.37
    は
    0.36
    ara
    0.35
    的文章
    0.34
    POSITIVE LOGITS
     a
    0.56
    지
    0.42
    T
    0.41
     for
    0.39
     alphabetical
    0.38
    ↵
    0.38
    z
    0.36
     endorsements
    0.35
    ed
    0.35
    an
    0.34
    Activations Density 0.130%

    No Known Activations