© 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. 10-GEMMASCOPE-RES-131K
    7. 10225
    Prev
    Next
    INDEX
    Explanations

    footballer, cricketer, volleyball

    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_10/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
     its
    -1.75
    mathrm
    -1.66
    它
    -1.63
     itself
    -1.52
    它的
    -1.46
     kwamba
    -1.43
     nying
    -1.40
     stiefel
    -1.38
     kuhusu
    -1.37
     it
    -1.32
    POSITIVE LOGITS
     from
    1.51
    конец
    1.42
    Bereich
    1.38
    besondere
    1.38
     remarqu
    1.36
     Krankheit
    1.35
     Чита
    1.35
     utama
    1.35
     memutus
    1.34
     "/";
    1.34
    Activations Density 0.158%

    No Known Activations