© 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. 91029
    Prev
    Next
    INDEX
    Explanations

    place names and numbers

    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
     ashamed
    -1.03
     insecure
    -0.97
     shame
    -0.90
     técnicas
    -0.86
     Self
    -0.84
     already
    -0.84
    ʺ
    -0.80
     harus
    -0.78
     herramientas
    -0.78
     Regent
    -0.78
    POSITIVE LOGITS
     Hr
    0.76
     émer
    0.74
     crème
    0.73
     yawn
    0.71
    Mentor
    0.71
    ді
    0.70
    doctype
    0.69
    рою
    0.68
     evoc
    0.67
    さい
    0.65
    Activations Density 0.018%

    No Known Activations