© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246513
    Prev
    Next
    INDEX
    Explanations

    pricing, exchange rate, Indonesian, Hindi

    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
     aport
    0.57
    四周
    0.51
     Marzo
    0.50
     vào
    0.47
    決勝
    0.46
    个
    0.46
    個
    0.45
     reconstruct
    0.45
     cá
    0.45
     المج
    0.44
    POSITIVE LOGITS
    alamat
    0.46
    achet
    0.45
     छंद
    0.44
    鲵
    0.44
    śli
    0.43
     छात्रा
    0.43
    jadi
    0.43
     মসজিদ
    0.42
    eker
    0.42
    नेहा
    0.42
    Activations Density 0.001%

    No Known Activations