© 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. 66386
    Prev
    Next
    INDEX
    Explanations

    Mend words and names

    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
    initial
    -0.97
     initial
    -0.88
    Initial
    -0.79
    shade
    -0.75
    aju
    -0.75
    sv
    -0.75
    achers
    -0.74
    better
    -0.74
     late
    -0.72
    tish
    -0.72
    POSITIVE LOGITS
     Diogo
    0.84
    衢
    0.72
     `{
    0.71
     Nez
    0.68
    igkeiten
    0.68
     Mend
    0.67
     Bruch
    0.67
     ‍
    0.66
    Scénario
    0.66
    eltjes
    0.66
    Activations Density 0.018%

    No Known Activations