© 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. 179120
    Prev
    Next
    INDEX
    Explanations

    gold, institutions, throttle, dragon, master, word, warm

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

    concepts and definitions

    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
     type
    0.48
     blockade
    0.47
     kinase
    0.46
     blockchain
    0.46
     ></
    0.46
     Sea
    0.45
     seminar
    0.45
     समुद्र
    0.45
     পাকিস্তান
    0.45
     closed
    0.44
    POSITIVE LOGITS
     טוב
    0.53
    キャンセル
    0.48
    寸法
    0.48
    È
    0.48
    子供
    0.48
    源
    0.47
     луч
    0.46
    謦
    0.46
    (^
    0.44
    봉
    0.44
    Activations Density 0.000%

    No Known Activations