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-16K
    4. 11665
    Prev
    Next
    INDEX
    Explanations

    "in-" prefix patterns

    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_16k_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
    OutputType
    0.45
    чном
    0.44
    роваться
    0.43
    وش
    0.41
    ાલ
    0.40
    震惊
    0.40
    㐄
    0.40
     Hrvatskoj
    0.39
    鍱
    0.39
     MainWindow
    0.38
    POSITIVE LOGITS
    quiries
    0.56
     vitro
    0.54
    idel
    0.51
     induct
    0.50
     insufficiently
    0.50
    site
    0.49
     nedenle
    0.49
    atrical
    0.49
     inim
    0.48
    herent
    0.48
    Activations Density 0.054%

    No Known Activations