© 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-65K
    7. 65121
    Prev
    Next
    INDEX
    Explanations

    detonate or explode

    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_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
     ваши
    0.47
     आपके
    0.45
     людям
    0.45
     люди
    0.45
    ቄ
    0.44
     বলেছিলেন
    0.44
     মানুষ
    0.43
    нице
    0.43
     মানুষের
    0.43
     الناس
    0.43
    POSITIVE LOGITS
     häufig
    0.42
     banjir
    0.39
     ayrıca
    0.39
     integración
    0.39
     swallowing
    0.38
     zwar
    0.38
     avanc
    0.38
    }$,
    0.37
     interfere
    0.37
    특히
    0.37
    Activations Density 0.012%

    No Known Activations