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. 100689
    Prev
    Next
    INDEX
    Explanations

    "I" or "you" to questions

    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
    𝐬
    0.52
    建筑物
    0.48
    Bott
    0.47
    시설
    0.46
     Woodlands
    0.45
    車站
    0.44
    设施
    0.44
    墙
    0.44
     रत्
    0.43
     Building
    0.43
    POSITIVE LOGITS
     myocardium
    0.50
    シンプル
    0.49
     weaken
    0.48
     hydrophobic
    0.47
     negotiate
    0.46
     sincere
    0.46
    シンプルな
    0.46
     weakness
    0.46
     chiedere
    0.46
     inquiet
    0.44
    Activations Density 0.014%

    No Known Activations