© 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
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 143
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     Treatment
    0.77
     Familie
    0.74
     Là
    0.71
    型
    0.70
    Yap
    0.69
    治療
    0.69
    加入
    0.68
     famous
    0.67
    配
    0.67
    分享
    0.65
    POSITIVE LOGITS
    शिंगटन
    1.28
    -;
    1.26
     impenetr
    1.23
     worsen
    1.22
    :>
    1.20
    洳
    1.19
    -,
    1.18
     inconven
    1.18
    जेक्ट
    1.18
     immédiatement
    1.17
    Activations Density 0.356%

    No Known Activations