© 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. 21841
    Prev
    Next
    INDEX
    Explanations

    code declarations

    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
     will
    -2.64
     immediately
    -1.78
     indicated
    -1.65
     using
    -1.64
     became
    -1.61
     riuscito
    -1.59
     cambiamento
    -1.55
     predominant
    -1.55
    OUBLE
    -1.54
     it
    -1.53
    POSITIVE LOGITS
     acqua
    1.45
     jotka
    1.38
    sometimes
    1.38
     大きい
    1.37
    生病
    1.37
     of
    1.36
     turmeric
    1.34
     frequentemente
    1.34
    greg
    1.34
    oli
    1.34
    Activations Density 0.048%

    No Known Activations