© 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. 113567
    Prev
    Next
    INDEX
    Explanations

    nested programming constructs

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

    the word "nested" or related concepts about nesting, hierarchies, or embedding structures within other structures.

    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
     soldat
    -2.69
    紲
    -2.55
     magasiner
    -2.53
    瓩
    -2.42
    揼
    -2.41
     brune
    -2.39
     vider
    -2.36
    獴
    -2.34
     batterie
    -2.30
    wifery
    -2.30
    POSITIVE LOGITS
    "
    2.72
    ’
    2.33
    ↵
    2.31
     =
    2.27
     других
    2.19
     ‚
    2.13
     )
    2.09
    ).
    2.06
     они
    2.06
     fünf
    2.05
    Activations Density 0.011%

    No Known Activations