© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41262
    Prev
    Next
    INDEX
    Explanations

    World Economic Forum (WEF)

    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_16_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
     परी
    0.55
    ği
    0.54
    ком
    0.53
    ನದ
    0.53
    ittances
    0.52
    ﻁ
    0.52
    眎
    0.52
    েক
    0.52
     Lieb
    0.52
    ianthus
    0.52
    POSITIVE LOGITS
     kul
    0.50
     crunch
    0.50
     crus
    0.50
     brainstorming
    0.49
     belongings
    0.48
     sporting
    0.48
    _
    0.48
    高铁
    0.48
     hoon
    0.48
     κινη
    0.47
    Activations Density 0.001%

    No Known Activations