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. 31-GEMMASCOPE-2-RES-262K
    4. 169424
    Prev
    Next
    INDEX
    Explanations

    Macaulay Collective animal

    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
    යෙන්
    0.45
    诸
    0.44
     ataupun
    0.42
     are
    0.41
    其中的
    0.41
    🕜
    0.41
     as
    0.40
    这项
    0.40
    ет
    0.39
     becomes
    0.39
    POSITIVE LOGITS
     Antennes
    0.50
    пись
    0.50
    inizi
    0.49
    lieder
    0.49
     גר
    0.48
    ত্রী
    0.48
     फ्रेम
    0.47
    entrada
    0.46
    新作
    0.46
    墒
    0.46
    Activations Density 0.000%

    No Known Activations