© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38941
    Prev
    Next
    INDEX
    Explanations

    years

    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_22/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
     year
    -0.97
    uerdo
    -0.97
     Year
    -0.90
    asthan
    -0.88
     after
    -0.86
    Ű
    -0.85
    .%
    -0.85
    fficacy
    -0.85
    georg
    -0.84
     子供
    -0.83
    POSITIVE LOGITS
     сьогодні
    0.97
     标题
    0.94
     arrayList
    0.94
     dekoratif
    0.92
     Baillargeon
    0.91
    <<<<<<<<<<<<
    0.91
    Recently
    0.88
    Fernseh
    0.86
     reaksi
    0.85
     Meksiko
    0.85
    Activations Density 0.075%

    No Known Activations