© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10502
    Prev
    Next
    INDEX
    Explanations

    dates and events

    np_acts-logits-general · gemini-2.5-flash-lite

    fine-tuning Google Bard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     २०२
    0.53
    ంట
    0.44
    bsite
    0.42
     Stiles
    0.41
     ২০১৯
    0.41
    🔄
    0.41
    🔟
    0.40
     ২০
    0.39
     """)
    0.39
    👥
    0.39
    POSITIVE LOGITS
     २०२२
    1.25
    <start_of_image>
    0.96
     ২০২২
    0.82
     Omicron
    0.54
    𓃵
    0.53
    Inflation
    0.50
    inflation
    0.49
    Monkey
    0.46
    
    0.44
    世界杯
    0.43
    Activations Density 0.106%

    No Known Activations