© 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. 12025
    Prev
    Next
    INDEX
    Explanations

    variable type declarations

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

    the word "type" in programming code or technical contexts, especially when used as a variable name, property, or attribute.

    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
      
    -3.08
    ?
    -2.80
     "
    -2.78
    ↵
    -2.58
       
    -2.56
         
    -2.55
                
    -2.41
    "
    -2.27
     $
    -2.23
    -
    -2.20
    POSITIVE LOGITS
    ꦫ
    2.56
     ||
    2.52
    type
    2.52
    ſu
    2.44
    酲
    2.39
    塤
    2.39
    er
    2.38
    ⢪
    2.38
    ⢊
    2.34
    琤
    2.30
    Activations Density 0.015%

    No Known Activations