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. 39206
    Prev
    Next
    INDEX
    Explanations

    respecting others' boundaries

    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
    ța
    0.42
    欣
    0.41
     স্থায়ী
    0.38
     glycolysis
    0.38
    ów
    0.37
     capacity
    0.37
    KeyboardView
    0.37
     sasane
    0.37
    宓
    0.36
     (%)
    0.36
    POSITIVE LOGITS
     les
    0.43
     entre
    0.41
     diante
    0.41
     predictably
    0.40
    。</
    0.40
    មុខ
    0.40
    前
    0.38
    Sheet
    0.38
     Catalan
    0.37
    spiration
    0.37
    Activations Density 0.001%

    No Known Activations