© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47858
    Prev
    Next
    INDEX
    Explanations

    a following significant descriptors

    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
    ctable
    -0.90
    ᵇ
    -0.85
     ukry
    -0.85
     adorable
    -0.84
     jonge
    -0.81
     popolare
    -0.80
     newly
    -0.79
    cute
    -0.79
     cantik
    -0.74
    يكب
    -0.73
    POSITIVE LOGITS
     productive
    2.11
     successful
    1.98
     busy
    1.96
     eventful
    1.86
     fruitful
    1.57
     busiest
    1.55
    productive
    1.54
    Successful
    1.48
     prosperous
    1.46
    successful
    1.43
    Activations Density 0.058%

    No Known Activations