© 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. 22-GEMMASCOPE-RES-131K
    4. 71567
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    飾り
    -0.98
     actes
    -0.87
     PROTEIN
    -0.86
    젼
    -0.86
     approximating
    -0.83
     unten
    -0.82
     spies
    -0.81
     ſtand
    -0.81
    sities
    -0.80
     เปิด
    -0.79
    POSITIVE LOGITS
     both
    1.00
     said
    0.96
     then
    0.94
     with
    0.88
     mainly
    0.85
    Needless
    0.83
    Both
    0.80
     подраз
    0.80
     as
    0.79
    americana
    0.79
    Activations Density 0.001%

    No Known Activations