© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    possessive followed by description

    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
    𝘀
    0.93
    𝚜
    0.93
    ſelf
    0.91
     own
    0.91
    ка
    0.91
    นี่
    0.89
     opponent
    0.88
    مود
    0.87
    ச்
    0.87
    ت
    0.86
    POSITIVE LOGITS
     내용을
    0.68
     width
    0.67
     complexities
    0.66
     contents
    0.65
    र्गत
    0.64
     কর্তৃপক্ষ
    0.63
     brunt
    0.63
     notch
    0.63
     befind
    0.62
     possibility
    0.62
    Activations Density 0.177%

    No Known Activations