© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52548
    Prev
    Next
    INDEX
    Explanations

    ".docx" or ".dot"

    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_65k_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
     légion
    0.50
     حقی
    0.48
     PlayerSelector
    0.48
    Ꮨ
    0.47
    ▍
    0.47
    탄소년
    0.47
    <bbox>
    0.46
    ⓪
    0.46
    粛
    0.45
     परप
    0.44
    POSITIVE LOGITS
    سم
    0.42
     göster
    0.39
    "
    0.39
     ห
    0.38
     lassen
    0.38
     e
    0.38
    cast
    0.38
    دار
    0.38
    ابل
    0.38
    en
    0.37
    Activations Density 0.001%

    No Known Activations