© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10468
    Prev
    Next
    INDEX
    Explanations

    "Our" + possessive nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     husband
    2.04
    ٨
    1.84
    ٥
    1.79
    ים
    1.78
    াযোগ
    1.77
     الأولى
    1.73
    в
    1.71
     wife
    1.65
     الأمر
    1.62
    جة
    1.62
    POSITIVE LOGITS
     نحن
    2.59
    ن
    2.38
    هایی
    2.38
    اً
    2.37
    self
    2.37
    spapers
    2.16
    יות
    2.11
    ted
    2.11
    ../../
    2.09
    jų
    2.08
    Activations Density 0.063%

    No Known Activations