© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93898
    Prev
    Next
    INDEX
    Explanations

    slice / pie / wedges

    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
    laise
    -0.76
     корпу
    -0.74
     أس
    -0.71
    liko
    -0.70
    ssymb
    -0.69
     корпуса
    -0.69
    recipient
    -0.68
    宸
    -0.68
    biol
    -0.67
    dash
    -0.67
    POSITIVE LOGITS
     slice
    2.95
     slices
    2.84
    slice
    2.55
    slices
    2.38
     Slice
    2.27
    Slice
    2.17
    Slices
    1.96
     slicing
    1.75
     pie
    1.59
     wedges
    1.58
    Activations Density 0.020%

    No Known Activations