© 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. 90622
    Prev
    Next
    INDEX
    Explanations

    entity names and suffixes

    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
     freshmen
    -0.80
    Representation
    -0.80
    ldre
    -0.77
     wick
    -0.77
     undergraduates
    -0.72
    मेल
    -0.72
     Coolidge
    -0.71
    企業
    -0.71
     Siena
    -0.71
     sages
    -0.69
    POSITIVE LOGITS
     decoding
    0.96
     decoder
    0.96
    [:,
    0.95
    eos
    0.93
     TEACHER
    0.90
     Beam
    0.90
     TEACHERS
    0.90
     teacher
    0.88
     previs
    0.87
     beam
    0.86
    Activations Density 0.004%

    No Known Activations