© 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. 34-GEMMASCOPE-RES-131K
    7. 83622
    Prev
    Next
    INDEX
    Explanations

    string concatenation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    開き
    -0.82
    neuri
    -0.75
     ofreciendo
    -0.72
     almendras
    -0.71
    shred
    -0.71
    obacteria
    -0.70
     exclusivamente
    -0.69
    aktif
    -0.68
    rense
    -0.68
     Meg
    -0.68
    POSITIVE LOGITS
    strcat
    2.61
     append
    2.52
     concatenation
    2.36
    concat
    2.33
    append
    2.25
     concat
    2.19
     appended
    2.16
     joining
    2.14
     concaten
    2.14
     concatenate
    2.06
    Activations Density 0.055%

    No Known Activations