© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40020
    Prev
    Next
    INDEX
    Explanations

    sports statistics

    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
     it
    -1.09
    を行い
    -1.06
     ส์
    -1.05
     determinado
    -1.00
     a
    -1.00
     determinados
    -0.99
    に入れる
    -0.98
    sized
    -0.98
    am
    -0.96
     <
    -0.96
    POSITIVE LOGITS
    wijl
    1.44
     termurah
    1.39
    참고
    1.30
    ﾍ
    1.29
     menatap
    1.28
     menyen
    1.25
    gın
    1.24
     terlaris
    1.22
     alkoholu
    1.20
     transparan
    1.19
    Activations Density 0.002%

    No Known Activations