© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12277
    Prev
    Next
    INDEX
    Explanations

    SQL, JavaScript, URLs

    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
     rápidas
    -1.50
     rapides
    -1.33
     acrí
    -1.29
     alkoh
    -1.28
     biela
    -1.26
    kese
    -1.23
     katkıda
    -1.23
     rápidos
    -1.23
    lampu
    -1.22
     exceptionnel
    -1.20
    POSITIVE LOGITS
    er
    1.31
    ung
    1.26
    ka
    1.23
    ans
    1.22
    ga
    1.20
    ku
    1.20
    ler
    1.19
    ole
    1.18
    le
    1.17
    plication
    1.17
    Activations Density 0.023%

    No Known Activations