© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3138
    Prev
    Next
    INDEX
    Explanations

    comparison or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     kriminal
    0.41
    并将
    0.35
    }={
    0.35
    エキス
    0.35
    𝖾
    0.34
    𝙝
    0.34
    𝙫
    0.34
     اكس
    0.34
     hahaha
    0.34
    🤲
    0.34
    POSITIVE LOGITS
     comparison
    0.66
     comparisons
    0.66
     superiority
    0.61
     Compared
    0.59
     비교
    0.59
     compar
    0.58
    Compared
    0.58
     Comparison
    0.57
     Comparisons
    0.57
     comparative
    0.57
    Activations Density 0.194%

    No Known Activations