© 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. 218252
    Prev
    Next
    INDEX
    Explanations

    predicament, ship, users, group, world, beverages, stated, died

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

    types of following what

    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
    ρη
    0.48
    刑
    0.47
    πο
    0.46
    敬
    0.45
    隊
    0.43
    potato
    0.42
    公
    0.42
    用
    0.41
    अभ
    0.41
    引用
    0.41
    POSITIVE LOGITS
    هایی
    0.53
    >©
    0.52
     عمل
    0.52
    cardo
    0.47
     kür
    0.47
     صورت
    0.46
     закончи
    0.46
     Threatened
    0.46
     تهد
    0.45
     कामों
    0.45
    Activations Density 0.001%

    No Known Activations