© 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. 2192
    Prev
    Next
    INDEX
    Explanations

    going or leaving

    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
     differentiated
    0.38
     অবদান
    0.35
     özelliği
    0.35
    特的
    0.34
     umiejęt
    0.34
     spineItem
    0.34
     współpracy
    0.34
    繹
    0.34
     funziona
    0.33
     LTS
    0.33
    POSITIVE LOGITS
    而去
    0.64
     away
    0.63
    离开
    0.63
    离开了
    0.62
     leaving
    0.61
     departure
    0.59
     meninggalkan
    0.59
     pergi
    0.58
    離開
    0.57
    去
    0.57
    Activations Density 0.066%

    No Known Activations