Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12216
    Prev
    Next
    INDEX
    Explanations

    Possessive and object pronouns

    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_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
     mówi
    0.45
     asked
    0.42
     insists
    0.41
     beschrieben
    0.41
    滨
    0.41
     errichtet
    0.41
     попыта
    0.41
     uite
    0.40
     says
    0.39
    宓
    0.39
    POSITIVE LOGITS
    Об
    0.42
    自身の
    0.42
    𝕆
    0.42
     guitars
    0.41
    EQU
    0.41
     ആള
    0.41
    !)
    0.41
    SqlQuery
    0.41
    ล
    0.40
    。)
    0.40
    Activations Density 0.037%

    No Known Activations