© 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. 17566
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    travel, plot, rights

    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
    َن
    0.52
     nettement
    0.46
     soggetto
    0.45
     آمد
    0.44
    न्देल
    0.44
     tuttavia
    0.44
     beden
    0.44
     viel
    0.43
    يته
    0.43
     بخش
    0.43
    POSITIVE LOGITS
    Đ
    0.45
    ਆ
    0.45
    По
    0.45
    В
    0.45
    功能
    0.44
    При
    0.44
    的
    0.43
    และ
    0.42
    공
    0.42
     एवं
    0.41
    Activations Density 0.000%

    No Known Activations