© 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. 108737
    Prev
    Next
    INDEX
    Explanations

    programming syntax entities

    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
    вия
    -0.81
    centerTitle
    -0.75
    å
    -0.72
     اس
    -0.72
     pà
    -0.71
     до
    -0.71
    اكم
    -0.70
     типу
    -0.69
     وليس
    -0.69
    того
    -0.69
    POSITIVE LOGITS
     kár
    0.89
    Filmography
    0.86
     kabát
    0.83
    észetes
    0.83
     picioare
    0.81
    繆
    0.81
     desperdic
    0.81
    Polen
    0.80
     наконец
    0.79
    "))
    0.79
    Activations Density 0.013%

    No Known Activations