© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17542
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and topic introductions

    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_40_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
    চ্ছা
    0.35
     ഒരിക്ക
    0.35
    [])
    0.34
    再一次
    0.32
     ন্য
    0.32
     Victim
    0.32
    ]]
    0.31
    ㅉ
    0.31
    Certain
    0.31
    гү
    0.31
    POSITIVE LOGITS
     আপনার
    1.15
    您的
    1.13
     your
    1.09
     вашего
    1.09
     आपके
    1.09
    你的
    1.08
     mentioned
    1.07
     вашей
    1.07
     आपकी
    1.05
    あなたの
    1.02
    Activations Density 0.028%

    No Known Activations