© 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. 61481
    Prev
    Next
    INDEX
    Explanations

    South Korea, currency, professions

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

    Yoon Suk-yeol, Bundang

    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
     ম্যাগ
    0.50
    عاية
    0.43
    aterials
    0.42
    মাত
    0.42
    ايا
    0.41
    ၺ
    0.40
    ミア
    0.40
    ቬ
    0.39
     unveiling
    0.39
    টিস
    0.39
    POSITIVE LOGITS
     строки
    0.39
    чну
    0.39
     focuss
    0.38
     квартиру
    0.38
    Roxy
    0.38
    ponder
    0.38
     sexe
    0.38
     constrain
    0.37
     αριθ
    0.37
    继承
    0.37
    Activations Density 0.009%

    No Known Activations