© 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. 22-GEMMASCOPE-RES-131K
    4. 36147
    Prev
    Next
    INDEX
    Explanations

    . followed by numbers or words

    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_22/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
     Brem
    -1.00
     Bapak
    -0.97
     santiago
    -0.97
     escritório
    -0.95
    ágok
    -0.94
     ayam
    -0.94
     powerful
    -0.94
     Fichier
    -0.93
     frankfurt
    -0.93
     ImageButton
    -0.93
    POSITIVE LOGITS
     wards
    1.06
     is
    1.05
     or
    1.00
    órica
    0.92
     которому
    0.88
     помню
    0.88
     парке
    0.85
    同时也
    0.83
     and
    0.83
     ему
    0.82
    Activations Density 0.007%

    No Known Activations