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. 29-GEMMASCOPE-2-RES-262K
    4. 52924
    Prev
    Next
    INDEX
    Explanations

    land, onshore, inland

    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_29_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
    টিউ
    0.72
    させていただ
    0.62
    ğimiz
    0.59
     характеризу
    0.59
    യിലാണ്
    0.59
    磋
    0.58
     میچ
    0.57
    गर्
    0.57
    늠
    0.56
    푀
    0.56
    POSITIVE LOGITS
     land
    3.67
    Land
    2.89
     Land
    2.84
    land
    2.79
     onshore
    2.69
     LAND
    2.53
    陆
    2.51
    陸
    2.49
    LAND
    2.47
     inland
    2.47
    Activations Density 0.051%

    No Known Activations