© 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. 12419
    Prev
    Next
    INDEX
    Explanations

    failures, deception, violations

    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
     will
    -1.32
     Однако
    -1.23
     hopefully
    -1.11
    もう少し
    -1.09
     like
    -1.05
    TOKYO
    -0.98
     azonban
    -0.98
    lüsse
    -0.97
    是大
    -0.95
    Однако
    -0.94
    POSITIVE LOGITS
    tôi
    1.22
     addirittura
    1.21
     bolsos
    1.21
    ग्री
    1.20
     toallas
    1.17
     Сергей
    1.14
     Meilleures
    1.12
    Cuándo
    1.11
    tily
    1.11
    never
    1.11
    Activations Density 0.055%

    No Known Activations