© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    code data structures like map

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

    generic type declarations in programming code, particularly angle brackets used for specifying type parameters in templates, maps, and collections.

    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
    ↵↵
    -1.80
            
    -1.63
        
    -1.57
         
    -1.48
     and
    -1.43
     karena
    -1.43
    -1.40
    moil
    -1.35
    vensko
    -1.34
     alebo
    -1.32
    POSITIVE LOGITS
     of
    2.11
    龑
    1.66
     innych
    1.48
     prêts
    1.44
    除此
    1.41
     havia
    1.40
     Kartoffeln
    1.38
    珖
    1.37
    走吧
    1.36
    Mereka
    1.30
    Activations Density 0.004%

    No Known Activations