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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3290
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and belonging

    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_22_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
     곳
    0.45
     부분
    0.44
    િયા
    0.44
     요소
    0.43
     bagay
    0.43
     itself
    0.43
     possibility
    0.41
     실행
    0.41
     있
    0.41
     możliwość
    0.41
    POSITIVE LOGITS
     own
    1.24
     respectivos
    0.92
     respective
    0.88
     собственные
    0.83
     Own
    0.79
     respectivas
    0.77
    respective
    0.74
     eigenes
    0.72
     собственных
    0.72
     jeweiligen
    0.71
    Activations Density 0.505%

    No Known Activations