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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4692
    Prev
    Next
    INDEX
    Explanations

    companies revolutionized worldwide

    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
    某个
    0.32
     glLightfv
    0.31
    त्रेयी
    0.31
     ≤
    0.31
    ことができます
    0.31
    ትክል
    0.31
     pointing
    0.30
     데
    0.30
     设置
    0.30
     lesión
    0.30
    POSITIVE LOGITS
     billionaire
    0.56
     billionaires
    0.55
     famously
    0.53
     revolutionized
    0.52
     worldwide
    0.51
     controvers
    0.50
    全球
    0.49
     unrival
    0.49
     miliardi
    0.48
     unrivalled
    0.46
    Activations Density 0.429%

    No Known Activations