© 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. 38298
    Prev
    Next
    INDEX
    Explanations

    various countable nouns

    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
     hohem
    -0.93
     estadounidense
    -0.88
     Wohnen
    -0.88
    一点点
    -0.85
     новая
    -0.83
     Thị
    -0.82
     שלהם
    -0.81
     dokonce
    -0.80
     высоким
    -0.80
     devlet
    -0.80
    POSITIVE LOGITS
     various
    1.22
    各種
    0.98
     både
    0.97
    ⲟ
    0.96
     things
    0.91
     objects
    0.90
    Banyak
    0.88
     everything
    0.86
    钣
    0.85
     items
    0.85
    Activations Density 0.152%

    No Known Activations