© 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. 33092
    Prev
    Next
    INDEX
    Explanations

    the common nouns

    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
    Adriana
    -0.90
    Spécification
    -0.85
    Também
    -0.81
     appreciably
    -0.81
     ESPEC
    -0.81
    Matéri
    -0.81
    Iglesia
    -0.80
    でも
    -0.79
    lendi
    -0.78
     overcrowding
    -0.78
    POSITIVE LOGITS
     environment
    1.09
     team
    1.00
     required
    0.96
    matics
    0.94
     system
    0.94
     Godhead
    0.91
     fleet
    0.90
     few
    0.90
     workforce
    0.90
    ms
    0.89
    Activations Density 0.094%

    No Known Activations