© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 12071
    Prev
    Next
    INDEX
    Explanations

    early 2024

    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_40_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
    早
    0.51
    न्ग
    0.46
    early
    0.46
     #-}
    0.42
    comboBox
    0.41
     early
    0.41
     ক্রোধ
    0.41
     早
    0.40
    ArrayAdapter
    0.38
     Rings
    0.38
    POSITIVE LOGITS
     quarter
    0.59
    quarter
    0.54
    Quarter
    0.51
    pel
    0.44
     Quarter
    0.44
    र्म
    0.43
    季度
    0.42
     전문
    0.42
     trimester
    0.42
     Monaten
    0.41
    Activations Density 0.028%

    No Known Activations