© 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. 115523
    Prev
    Next
    INDEX
    Explanations

    either version 2 or 3

    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
    ਇ
    -0.91
    =============
    -0.88
    riebene
    -0.87
    ===============
    -0.85
    sepeda
    -0.84
    Matt
    -0.84
    Things
    -0.83
    WHILE
    -0.83
     hendes
    -0.82
    Ꭼ
    -0.82
    POSITIVE LOGITS
     since
    0.86
    zipped
    0.80
     kaikk
    0.78
    Steal
    0.75
     gondol
    0.74
    alige
    0.74
     Bib
    0.73
     mivel
    0.70
    ள்ள
    0.69
    ystic
    0.69
    Activations Density 0.004%

    No Known Activations