© 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. 119952
    Prev
    Next
    INDEX
    Explanations

    code keywords programming control flow

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

    code block indentation or whitespace preceding control flow statements like "if", "else", "elif", and loop 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
    lili
    -1.26
     sentiers
    -1.23
     VILLA
    -1.21
    莇
    -1.21
    咈
    -1.20
    梛
    -1.18
     WATERS
    -1.16
    such
    -1.16
     viſ
    -1.16
     المنتج
    -1.14
    POSITIVE LOGITS
    ’
    1.54
     his
    1.41
     different
    1.34
     each
    1.32
     It
    1.30
     various
    1.27
     are
    1.26
     Each
    1.25
     vielfäl
    1.24
     with
    1.23
    Activations Density 0.009%

    No Known Activations