© 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. 75321
    Prev
    Next
    INDEX
    Explanations

    "X stands for/means Y"

    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
     zj
    -1.07
     and
    -0.94
     França
    -0.93
    未満
    -0.90
    television
    -0.90
    rions
    -0.86
     vred
    -0.86
     októ
    -0.86
    posables
    -0.86
    FromDB
    -0.81
    POSITIVE LOGITS
    是一种
    1.05
     ajouté
    1.03
    是一個
    1.02
     gewähr
    0.98
     kvinna
    0.98
     står
    0.97
     partire
    0.94
     rifer
    0.93
     fungerar
    0.92
     pierde
    0.91
    Activations Density 0.062%

    No Known Activations