© 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. 11057
    Prev
    Next
    INDEX
    Explanations

    when and how

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

    when explanations

    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
    Chal
    0.38
     NAMES
    0.37
    ("'
    0.37
     հատ
    0.37
    ᔪ
    0.37
    चल
    0.36
     upon
    0.36
     unexplored
    0.34
    粗
    0.34
    ದುಕ
    0.33
    POSITIVE LOGITS
    什么时候
    2.45
    何时
    2.42
     কখন
    2.05
     timing
    2.03
     cuándo
    2.02
     Timing
    1.93
     কবে
    1.91
    timing
    1.87
    タイミング
    1.87
    Timing
    1.84
    Activations Density 0.326%

    No Known Activations