© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113883
    Prev
    Next
    INDEX
    Explanations

    code blocks with strings

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

    string literals in code, especially those appearing after assignment operators or as function arguments.

    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
     I
    -1.82
     is
    -1.48
    และ
    -1.46
    ``
    -1.44
                
    -1.34
                    
    -1.30
     и
    -1.24
    เรา
    -1.24
            
    -1.23
    可能
    -1.23
    POSITIVE LOGITS
    Étymologie
    1.54
     after
    1.49
     pretože
    1.39
     when
    1.37
     которы
    1.35
     Several
    1.34
    çou
    1.33
    近くに
    1.33
    Transcripción
    1.32
    会在
    1.30
    Activations Density 0.108%

    No Known Activations