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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118890
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    Java and programming annotations, particularly those indicating metadata or decorator patterns (like `@Before`, `@After`, `@Implements`, `@Tested`, `@Produces`, and similar annotation syntax).

    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
    <td>
    -1.50
    jTable
    -1.42
     redenen
    -1.41
    ܊
    -1.40
     dieťa
    -1.37
    𓇼
    -1.36
     saati
    -1.35
    ৄ
    -1.33
     poë
    -1.33
     flotte
    -1.33
    POSITIVE LOGITS
     but
    1.46
     said
    1.45
    s
    1.44
     staunch
    1.41
    This
    1.31
     என்ப
    1.31
     recherchez
    1.30
    It
    1.28
     [
    1.27
     gleiche
    1.21
    Activations Density 0.018%

    No Known Activations