© 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-65K
    7. 211
    Prev
    Next
    INDEX
    Explanations

    data and code

    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_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
    지는
    0.42
    ан
    0.34
    :
    0.33
    い
    0.33
    alı
    0.32
    지만
    0.31
    지를
    0.31
    T
    0.31
     detract
    0.30
     ۔
    0.30
    POSITIVE LOGITS
     Data
    0.50
    data
    0.49
    на
    0.42
    1
    0.42
     getData
    0.42
     data
    0.42
    ะ
    0.41
    Data
    0.41
     Aplikasi
    0.39
    า
    0.38
    Activations Density 0.925%

    No Known Activations