© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159955
    Prev
    Next
    INDEX
    Explanations

    wooden ships, stars, Buddhist, stung

    np_acts-logits-general · gemini-2.5-flash-lite

    why it saw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icación
    0.45
    %.
    0.43
    ước
    0.43
     horrors
    0.43
    ЗО
    0.42
    नगर
    0.41
    ξε
    0.41
    रात
    0.40
    炁
    0.39
    at
    0.39
    POSITIVE LOGITS
     Abhäng
    0.56
    因而
    0.52
     Поэтому
    0.48
    の間
    0.48
    </h3>
    0.46
     因此
    0.46
     siedz
    0.46
    依赖
    0.45
     Wohnung
    0.45
     شوق
    0.45
    Activations Density 0.001%

    No Known Activations