© 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. 23835
    Prev
    Next
    INDEX
    Explanations

    LaTeX preamble and code definitions

    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
     adorno
    -0.96
     traje
    -0.85
     clouds
    -0.84
     AÑOS
    -0.83
     urbano
    -0.82
     Kav
    -0.81
     pega
    -0.80
     both
    -0.79
     fuma
    -0.78
     morada
    -0.77
    POSITIVE LOGITS
    SupportActionBar
    0.86
    ډ
    0.86
    ruary
    0.84
     gescha
    0.82
     ABSOL
    0.82
    Valentina
    0.81
     Cp
    0.80
     simplemente
    0.78
     HRT
    0.77
     búsquedas
    0.77
    Activations Density 0.001%

    No Known Activations