© 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. 57232
    Prev
    Next
    INDEX
    Explanations

    common sentence continuations

    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
     राशियों
    0.44
     olefins
    0.42
     lingua
    0.39
    ↵↵
    0.39
     swallow
    0.39
     রোহিঙ্গ
    0.39
     性
    0.38
     dumpster
    0.38
    ↵
    0.38
     someday
    0.38
    POSITIVE LOGITS
    Een
    0.51
     goede
    0.49
    Deze
    0.46
    Một
    0.45
    蚋
    0.44
     Copies
    0.43
    Eine
    0.43
    槁
    0.43
    Чем
    0.43
    जन्म
    0.42
    Activations Density 0.013%

    No Known Activations