© 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. 34-GEMMASCOPE-RES-131K
    7. 48837
    Prev
    Next
    INDEX
    Explanations

    string concatenation with plus

    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
     británica
    -0.84
     kwargs
    -0.82
    ]-
    -0.79
     zimowe
    -0.78
    🐫
    -0.77
     traseira
    -0.76
    ArrowToggle
    -0.76
    kwargs
    -0.75
    unaga
    -0.75
    чется
    -0.74
    POSITIVE LOGITS
     +
    2.52
     $+$
    1.63
     $+\
    1.60
     plus
    1.56
     плюс
    1.40
    ()+"
    1.34
    +"
    1.33
    }+\
    1.30
     +
    1.30
    +
    1.27
    Activations Density 0.069%

    No Known Activations