© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102612
    Prev
    Next
    INDEX
    Explanations

    package os and utility

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

    the `<utility>` header include statement in C++ code.

    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
     provide
    -1.83
     and
    -1.58
     nine
    -1.52
    ”。
    -1.47
     time
    -1.45
     often
    -1.45
     offer
    -1.43
    .......
    -1.39
     had
    -1.38
     пре
    -1.38
    POSITIVE LOGITS
     conseguenze
    1.82
    HEE
    1.72
     nuove
    1.70
     sarebbe
    1.70
     ridiculously
    1.66
    trás
    1.64
     Anſ
    1.63
    ፨
    1.59
     جدید
    1.58
    primarily
    1.57
    Activations Density 0.001%

    No Known Activations