© 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. 78186
    Prev
    Next
    INDEX
    Explanations

    exhibited abstract qualities

    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
     قدر
    -0.85
    wrote
    -0.85
    ագրություններ
    -0.79
    bux
    -0.79
    Ṡ
    -0.78
    GetField
    -0.77
    bram
    -0.77
    の概要
    -0.76
    靶
    -0.75
     MAGAZINE
    -0.75
    POSITIVE LOGITS
     exhibited
    4.63
     displayed
    4.44
    displayed
    3.36
     demonstrated
    3.34
     shown
    3.09
    Displayed
    3.02
     display
    2.80
     exhibit
    2.73
     exhib
    2.44
     showed
    2.34
    Activations Density 0.139%

    No Known Activations