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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33389
    Prev
    Next
    INDEX
    Explanations

    different or these

    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
     parfum
    -0.96
     chanson
    -0.95
     endian
    -0.91
     fillets
    -0.91
     classifica
    -0.90
    沼
    -0.88
    bVar
    -0.87
     documenta
    -0.87
     می‌توان
    -0.85
     langage
    -0.85
    POSITIVE LOGITS
    這些
    1.47
     these
    1.29
     этих
    1.26
    These
    1.26
    这些
    1.26
     różnych
    1.18
    これらの
    1.12
     Эти
    1.07
    はっきり
    1.05
     различных
    1.01
    Activations Density 0.079%

    No Known Activations