© 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-65K
    7. 13188
    Prev
    Next
    INDEX
    Explanations

    size and dimensions

    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_65k_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
    W
    0.63
    G
    0.52
    ށް
    0.48
    V
    0.47
    તે
    0.47
    نو
    0.47
    ورد
    0.46
    نية
    0.45
    9
    0.45
     suave
    0.44
    POSITIVE LOGITS
     size
    1.85
     SIZE
    1.75
     Size
    1.72
     sizes
    1.66
    size
    1.62
    サイズ
    1.57
     tamaño
    1.54
     размера
    1.53
     размеры
    1.52
     размер
    1.51
    Activations Density 0.193%

    No Known Activations