© 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
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 10644
    Prev
    Next
    INDEX
    Explanations

    if any

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

    not empty or null

    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
     lacked
    0.57
    없는
    0.55
     lacks
    0.54
     없어
    0.52
    少了
    0.51
    없
    0.50
     없다
    0.49
     குறைவாக
    0.49
    没什么
    0.48
     dearth
    0.47
    POSITIVE LOGITS
     nonzero
    1.71
    nonzero
    1.60
    isNotEmpty
    1.38
     nonempty
    1.23
    NotEmpty
    1.22
     nontrivial
    1.20
     nonEmpty
    1.17
     !=
    1.16
    NotNull
    1.14
    ≠
    1.09
    Activations Density 0.146%

    No Known Activations