© 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. 1733
    Prev
    Next
    INDEX
    Explanations

    string building

    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
    зик
    -0.84
    papel
    -0.80
    جز
    -0.80
     kvin
    -0.79
    kamen
    -0.78
    ünst
    -0.77
    tent
    -0.77
     चल
    -0.76
    DAN
    -0.75
     Mish
    -0.75
    POSITIVE LOGITS
     sb
    1.48
     StringBuilder
    1.36
     SB
    1.33
     builder
    1.27
    StringBuilder
    1.16
    sb
    1.13
    SB
    1.13
    stringBuilder
    1.09
     stringBuilder
    1.06
    builder
    1.05
    Activations Density 0.002%

    No Known Activations