© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6192
    Prev
    Next
    INDEX
    Explanations

    declaring and using variables

    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_40_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
     церковь
    0.39
    崇
    0.38
    petit
    0.37
    圏
    0.36
    ビーチ
    0.36
    映画
    0.35
     yeasts
    0.35
    夢
    0.35
    防水
    0.35
     سانت
    0.35
    POSITIVE LOGITS
     variables
    1.88
     variable
    1.78
    变量
    1.73
     Variables
    1.70
     Variablen
    1.64
    Variables
    1.62
     variáveis
    1.60
     variabel
    1.59
    変数
    1.59
     Variable
    1.56
    Activations Density 0.181%

    No Known Activations