© 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. 34-GEMMASCOPE-RES-131K
    7. 73647
    Prev
    Next
    INDEX
    Explanations

    latex or technical commands

    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_34/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
    surate
    -0.94
    azzle
    -0.88
     rapidement
    -0.83
    никам
    -0.83
     frontman
    -0.80
     traité
    -0.78
     octopus
    -0.77
    incidence
    -0.76
    oría
    -0.76
    éal
    -0.75
    POSITIVE LOGITS
     its
    0.93
    †
    0.87
     அத
    0.82
    娯
    0.82
     đổi
    0.82
     đặt
    0.82
     moderately
    0.79
     Freuden
    0.77
    Penalty
    0.77
     contrasting
    0.77
    Activations Density 0.028%

    No Known Activations