© 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. 129795
    Prev
    Next
    INDEX
    Explanations

    percentage of cases

    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
     is
    -0.96
    ditor
    -0.95
    mmation
    -0.90
    وقد
    -0.87
    teness
    -0.84
    athread
    -0.84
     nuovamente
    -0.83
    부터
    -0.81
    pening
    -0.81
    είου
    -0.80
    POSITIVE LOGITS
     today
    1.05
     aujourd
    0.97
    miyorum
    0.94
     the
    0.94
     épaules
    0.91
     fotogra
    0.90
    fera
    0.88
    Kv
    0.88
     komer
    0.87
    today
    0.87
    Activations Density 0.074%

    No Known Activations