© 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. 93057
    Prev
    Next
    INDEX
    Explanations

    code annotations descriptor

    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
     get
    -1.14
    ifikasi
    -1.10
    Identyfik
    -1.08
     Iš
    -1.07
    唧
    -1.06
    Их
    -1.02
    Тогда
    -0.95
    使其
    -0.94
     ventre
    -0.94
    علی
    -0.94
    POSITIVE LOGITS
     konusunda
    1.12
     also
    1.09
     氏
    1.08
     queste
    1.08
     sienta
    1.07
     richiesto
    1.06
     interesantes
    1.06
     некоторых
    1.05
     chiese
    1.05
     mencionó
    1.05
    Activations Density 0.001%

    No Known Activations