© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98779
    Prev
    Next
    INDEX
    Explanations

    trees seemed to shift

    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_40_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
    sendKeyDown
    0.41
    ()<
    0.39
    ntag
    0.38
     solos
    0.37
    готовки
    0.37
    scalars
    0.36
    OB
    0.36
     classically
    0.36
     conventionally
    0.36
     दिवंगत
    0.36
    POSITIVE LOGITS
    捚
    0.46
     അനു
    0.43
     proib
    0.42
     Denim
    0.41
     এই
    0.41
     bandana
    0.40
     घटना
    0.39
     সকলকে
    0.39
     todos
    0.38
     pretending
    0.38
    Activations Density 0.012%

    No Known Activations