© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7582
    Prev
    Next
    INDEX
    Explanations

    possessive descriptions

    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_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
    kannya
    0.88
     yǔ
    0.84
    т
    0.83
    lom
    0.82
    <unused597>
    0.81
    lemy
    0.78
    <unused1020>
    0.78
    லக
    0.78
     WHY
    0.75
    න්නේ
    0.74
    POSITIVE LOGITS
     their
    1.13
     his
    1.05
    Their
    0.94
    他們的
    0.91
     who
    0.90
     njihov
    0.88
     whom
    0.86
     jejich
    0.85
     njegov
    0.85
    他们的
    0.83
    Activations Density 0.054%

    No Known Activations