© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4261
    Prev
    Next
    INDEX
    Explanations

    gr/гра after activating words

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

    gra / Gr words followed by specific concepts

    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_53_width_65k_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
    वळ
    0.47
     世
    0.38
    轫
    0.38
     torchvision
    0.37
     ويكيميديا
    0.36
     chart
    0.36
     dibujos
    0.36
     المصفوفه
    0.36
    ︹
    0.35
    សម្រ
    0.35
    POSITIVE LOGITS
     гра
    3.33
     Гра
    2.94
    GR
    2.78
    гра
    2.75
     GRA
    2.73
    GRA
    2.73
    Gr
    2.72
    グラ
    2.72
     GR
    2.70
    Gran
    2.70
    Activations Density 0.403%

    No Known Activations