© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4421
    Prev
    Next
    INDEX
    Explanations

    brick construction

    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_16_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
    is
    1.01
    지
    0.93
    ต์
    0.91
    A
    0.86
    डी
    0.85
    X
    0.84
     biodegrad
    0.81
    ف
    0.80
    RA
    0.78
    და
    0.78
    POSITIVE LOGITS
     brick
    1.26
     Brick
    1.17
    Brick
    1.10
     bricks
    1.06
    砖
    0.96
     кирпи
    0.95
    brick
    0.95
    磚
    0.92
    örungen
    0.83
    ъ
    0.79
    Activations Density 0.002%

    No Known Activations