© 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. 31-GEMMASCOPE-2-RES-65K
    7. 20695
    Prev
    Next
    INDEX
    Explanations

    water until

    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
     coalesce
    0.41
     magasins
    0.41
     `=`
    0.41
     حداقل
    0.40
     finer
    0.39
     magasin
    0.39
     atleast
    0.38
     গাড়ি
    0.38
     নগ
    0.37
     RBS
    0.37
    POSITIVE LOGITS
    click
    0.48
    с
    0.46
    ه‌ها
    0.46
    imu
    0.43
    kinase
    0.43
    ofType
    0.41
    metry
    0.40
    াপি
    0.40
    ardonnay
    0.40
    imer
    0.39
    Activations Density 0.001%

    No Known Activations