© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101327
    Prev
    Next
    INDEX
    Explanations

    java imports

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

    Java import statements, particularly with high activation immediately after the "import" keyword and following periods in package names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -1.73
    销量
    -1.26
     diğer
    -1.25
     telas
    -1.25
    其他的
    -1.23
    شة
    -1.22
    IANGLES
    -1.22
     รถ
    -1.21
    右
    -1.20
     fenó
    -1.19
    POSITIVE LOGITS
     together
    1.48
     ২০
    1.40
     along
    1.31
    ",
    1.26
     they
    1.24
    swire
    1.23
    with
    1.23
    стью
    1.17
    essentiel
    1.16
    cip
    1.15
    Activations Density 0.018%

    No Known Activations