Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49024
    Prev
    Next
    INDEX
    Explanations

    dragging through

    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
     परस्मैपदी
    0.42
    ීමට
    0.41
     عليهم
    0.39
     armament
    0.39
    靂
    0.39
     comunicar
    0.38
     চাপে
    0.38
    馭
    0.38
     cerebral
    0.38
    ээр
    0.37
    POSITIVE LOGITS
    drag
    0.67
     drag
    0.64
     dragged
    0.64
     Drag
    0.62
    拖
    0.61
     dragging
    0.56
     drags
    0.54
    Dragged
    0.53
    Drag
    0.50
    dragging
    0.46
    Activations Density 0.051%

    No Known Activations