© 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. 5497
    Prev
    Next
    INDEX
    Explanations

    counting numbers after "**"

    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
    ╕
    0.49
     则
    0.46
     quát
    0.46
     rồi
    0.45
     použ
    0.45
     வளாக
    0.45
    하시면
    0.44
    用い
    0.44
     súa
    0.44
     ñ
    0.44
    POSITIVE LOGITS
    ات
    0.60
    지
    0.50
    𝓭
    0.49
     ਦਵਾਈ
    0.49
     analyser
    0.48
    두
    0.47
    ਨਾ
    0.47
     इतिहास
    0.46
    ارد
    0.46
    ਚ
    0.46
    Activations Density 0.001%

    No Known Activations