© 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. 100184
    Prev
    Next
    INDEX
    Explanations

    popular, global, found, design, orbit

    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
    الف
    0.49
     genética
    0.46
    والفق
    0.43
    રા
    0.43
    िलों
    0.43
     plateforme
    0.43
    iciencia
    0.42
    چ
    0.42
    addEnemy
    0.41
    ígen
    0.41
    POSITIVE LOGITS
     вз
    0.47
     bit
    0.46
     начин
    0.46
    顐
    0.46
     изме
    0.44
     төр
    0.43
    aes
    0.41
    ття
    0.41
     але
    0.41
     Orbit
    0.41
    Activations Density 0.002%

    No Known Activations