© 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. 4514
    Prev
    Next
    INDEX
    Explanations

    marriage and related concepts

    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
    ۔
    0.66
    ።
    0.52
    是
    0.52
    ي
    0.47
     glared
    0.46
     രോഗ
    0.46
    iędzy
    0.46
    ва
    0.45
    。「
    0.44
     róż
    0.44
    POSITIVE LOGITS
    u
    0.77
     I
    0.65
    h
    0.61
    ation
    0.57
    able
    0.52
    as
    0.51
    could
    0.51
     Marriage
    0.50
    at
    0.50
    ↵
    0.49
    Activations Density 0.009%

    No Known Activations