© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 224729
    Prev
    Next
    INDEX
    Explanations

    building lists of concepts

    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
     articulation
    0.38
     computing
    0.38
     lẻ
    0.37
     freshwater
    0.36
    ག
    0.36
    ஒ
    0.35
    interpreter
    0.35
     dissipation
    0.35
     realization
    0.34
     deline
    0.34
    POSITIVE LOGITS
    कांची
    0.40
    刪
    0.40
    这是一
    0.39
    👑
    0.38
    т
    0.38
    oter
    0.38
    τών
    0.38
    லிய
    0.37
     Kiwi
    0.37
    ιών
    0.37
    Activations Density 0.000%

    No Known Activations