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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71318
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mpeg
    0.42
     nanof
    0.42
     lacer
    0.41
     Thermodynamics
    0.40
     цей
    0.39
    ▛
    0.39
     pulsed
    0.39
    ｗｗ
    0.39
     forceps
    0.39
     pollen
    0.38
    POSITIVE LOGITS
     밝혔
    0.50
     Гор
    0.46
     oftent
    0.46
    ุ
    0.46
     contraste
    0.44
    ברו
    0.44
    sG
    0.43
    قال
    0.43
    من
    0.42
     ancienne
    0.42
    Activations Density 0.005%

    No Known Activations