© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    locations, series, and abstract 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_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
    fill
    0.47
    ıyı
    0.46
    h
    0.46
    filling
    0.45
    s
    0.45
    statusCode
    0.45
    eating
    0.44
    Aula
    0.43
    hä
    0.43
     запол
    0.42
    POSITIVE LOGITS
     contacted
    0.48
     Bij
    0.47
    獣
    0.46
    퀸
    0.46
     اثر
    0.46
    ຕິດຕໍ່
    0.46
     lined
    0.46
    벽
    0.46
    飩
    0.46
     बीमारियों
    0.45
    Activations Density 0.001%

    No Known Activations