© 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. 11146
    Prev
    Next
    INDEX
    Explanations

    script tags or parameters (function, file, format)

    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
    ếng
    -1.02
    nitzer
    -0.93
     Ι
    -0.91
    ŚĆ
    -0.90
     time
    -0.88
    IconModule
    -0.88
     Padding
    -0.87
     only
    -0.86
    (".",
    -0.85
     endforeach
    -0.83
    POSITIVE LOGITS
    дры
    1.02
    都已经
    1.00
    itability
    0.98
    谙
    0.98
    自体は
    0.95
     hés
    0.93
     obrigado
    0.91
     hoje
    0.91
     oferta
    0.90
    Conse
    0.89
    Activations Density 0.003%

    No Known Activations