© 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. 11972
    Prev
    Next
    INDEX
    Explanations

    calling functions or methods

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

    function or method invocations in programming code, particularly those containing underscores or following "call" patterns.

    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
     крепления
    -2.22
    medriver
    -2.20
    useppe
    -1.88
     ある
    -1.88
     можете
    -1.84
    ̭
    -1.82
     décembre
    -1.80
     personalizadas
    -1.79
    you
    -1.77
    賒
    -1.77
    POSITIVE LOGITS
     freaking
    2.44
     multitude
    2.02
    焄
    1.99
    眼下
    1.99
     dips
    1.91
     frig
    1.88
    雱
    1.87
    capace
    1.82
    籴
    1.80
     freakin
    1.77
    Activations Density 0.030%

    No Known Activations