© 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. 26280
    Prev
    Next
    INDEX
    Explanations

    definitions and translations

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

    translations and foreign language phrases

    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
    চেতন
    0.43
    👇
    0.43
    ⃣
    0.41
     👇
    0.40
    ध्ये
    0.39
    ικός
    0.39
    🔽
    0.39
     พิจ
    0.39
    iselt
    0.39
     reconsider
    0.37
    POSITIVE LOGITS
     यानी
    0.92
     yani
    0.89
     czyli
    0.79
    翻译
    0.77
     тобто
    0.75
     ("
    0.75
     translates
    0.73
    অর্থাৎ
    0.73
     (=
    0.72
    ("
    0.71
    Activations Density 0.095%

    No Known Activations