© 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. 15593
    Prev
    Next
    INDEX
    Explanations

    countries and people

    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
    Anime
    0.58
    Telefono
    0.57
    Comunic
    0.55
    México
    0.55
    鬨
    0.55
    Bs
    0.54
    Penumpang
    0.54
     любят
    0.54
    倰
    0.54
    landı
    0.53
    POSITIVE LOGITS
     simulation
    0.55
     sle
    0.53
     computer
    0.50
     library
    0.49
     artifacts
    0.48
     software
    0.48
     optical
    0.48
     grievous
    0.47
     yield
    0.47
     artifact
    0.46
    Activations Density 0.001%

    No Known Activations