© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119864
    Prev
    Next
    INDEX
    Explanations

    code structures

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

    opening curly braces that start object or block definitions in 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
     which
    -2.34
     often
    -2.09
     also
    -2.08
     it
    -1.95
     five
    -1.91
     whose
    -1.87
     or
    -1.84
     with
    -1.83
     nine
    -1.80
     eight
    -1.75
    POSITIVE LOGITS
    睃
    1.51
     incluida
    1.44
     ווע
    1.43
     طريقة
    1.41
    AFTER
    1.41
    颪
    1.41
    狳
    1.38
    の上に
    1.34
    谖
    1.32
     ture
    1.31
    Activations Density 0.030%

    No Known Activations