© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58792
    Prev
    Next
    INDEX
    Explanations

    equation tags (number)

    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
     used
    -0.90
     last
    -0.82
     couldn
    -0.78
    <bos>
    -0.77
     that
    -0.76
     In
    -0.76
     those
    -0.75
     понятия
    -0.75
     modeli
    -0.74
    ですので
    -0.73
    POSITIVE LOGITS
     ochran
    1.10
     tenisky
    0.98
     AssemblyCompany
    0.97
     obuv
    0.97
     médicament
    0.96
    📤
    0.96
    鳅
    0.93
     podoba
    0.93
    InjectMocks
    0.92
     estrellas
    0.91
    Activations Density 0.005%

    No Known Activations