© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    path separators or slashes

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

    string literals or paths that end with a closing delimiter (like quotes, parentheses, or angle brackets).

    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
     alip
    -2.02
     camiset
    -1.86
    桖
    -1.83
    涐
    -1.78
     teater
    -1.77
     stiker
    -1.77
     hawa
    -1.75
     wako
    -1.74
     chini
    -1.73
     gani
    -1.73
    POSITIVE LOGITS
     also
    2.39
            
    2.03
    }$,
    1.98
     It
    1.91
           
    1.73
     as
    1.73
          
    1.72
         
    1.70
     are
    1.68
       
    1.66
    Activations Density 0.057%

    No Known Activations