© 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. 130495
    Prev
    Next
    INDEX
    Explanations

    organization

    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
     of
    -1.56
     pecuni
    -1.43
    They
    -1.30
     octavia
    -1.24
    ньому
    -1.17
     like
    -1.17
     gratific
    -1.17
    🕗
    -1.16
     навіть
    -1.12
    Other
    -1.11
    POSITIVE LOGITS
     its
    1.59
     automático
    1.30
     conectado
    1.25
     l
    1.23
     relacionado
    1.22
     aliado
    1.17
     hidráulica
    1.17
    了几
    1.17
     itself
    1.16
    裏
    1.15
    Activations Density 0.197%

    No Known Activations