Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 17188
    Prev
    Next
    INDEX
    Explanations

    union type

    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
    REW
    0.40
    ಕಾರ
    0.39
     patric
    0.38
     cellulosic
    0.38
    뢰
    0.38
     Caribbean
    0.38
     unmodified
    0.38
     Woodlands
    0.37
     ICA
    0.37
    勛
    0.37
    POSITIVE LOGITS
     union
    0.91
     unions
    0.87
    Union
    0.84
     Unions
    0.81
     Union
    0.81
     यूनियन
    0.80
    union
    0.74
     discriminated
    0.73
     TypeScript
    0.66
     intersected
    0.66
    Activations Density 0.022%

    No Known Activations