© 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. 30712
    Prev
    Next
    INDEX
    Explanations

    image file types (jpeg, png, gif)

    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
     projectile
    -0.94
    釀
    -0.86
     معه
    -0.85
    assertArray
    -0.82
    elve
    -0.81
     denke
    -0.81
    カップル
    -0.80
    antart
    -0.80
    LocalTime
    -0.79
    pregnant
    -0.79
    POSITIVE LOGITS
    jpeg
    1.02
    挽回
    0.83
     jpeg
    0.79
     png
    0.78
     характеристи
    0.77
    illies
    0.76
    png
    0.76
    Gif
    0.74
     gif
    0.73
     रंग
    0.71
    Activations Density 0.009%

    No Known Activations