© 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. 11099
    Prev
    Next
    INDEX
    Explanations

    initializer or builder method context

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

    words related to software components and objects in code, particularly "Bundle", "Builder", "loop", "communicator", "Comm", "arena", "Context", "env", and "Center".

    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
    -1.62
     about
    -1.54
     použí
    -1.42
     sensazione
    -1.38
     the
    -1.37
    孥
    -1.36
     kämp
    -1.36
    伋
    -1.33
     pomaga
    -1.33
    impôt
    -1.32
    POSITIVE LOGITS
    炽
    1.53
     varandra
    1.51
     nästa
    1.47
    ogues
    1.39
    强者
    1.35
    几分
    1.34
    .
    1.27
    鱿
    1.27
    骤
    1.24
    tones
    1.23
    Activations Density 0.034%

    No Known Activations