© 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. 31-GEMMASCOPE-2-RES-65K
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns in multiple languages

    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_65k_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
    h
    0.52
    l
    0.48
    ing
    0.48
    .
    0.47
    <ul>
    0.43
    0
    0.42
    ize
    0.42
     specify
    0.41
    che
    0.41
    y
    0.41
    POSITIVE LOGITS
     этом
    0.69
     этой
    0.65
     this
    0.64
     этого
    0.62
     هذا
    0.57
     dieser
    0.57
     هذه
    0.55
     diesem
    0.55
    这话
    0.55
     questa
    0.54
    Activations Density 0.031%

    No Known Activations