© 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. 16-GEMMASCOPE-2-RES-262K
    7. 13487
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and definitions

    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_16_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
     wann
    0.63
    o
    0.56
    et
    0.52
     persuasive
    0.52
    er
    0.51
    ate
    0.50
    ing
    0.50
    remain
    0.50
     lectures
    0.50
    mon
    0.49
    POSITIVE LOGITS
    我们
    0.53
    ून
    0.51
    我們
    0.49
    䀼
    0.48
    兟
    0.48
     HashTable
    0.47
    ພວກເຮົາ
    0.47
    الغ
    0.47
    سا
    0.47
     Livestock
    0.47
    Activations Density 0.000%

    No Known Activations