© 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. 38488
    Prev
    Next
    INDEX
    Explanations

    Q: or A:

    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
    tablir
    -0.85
    changers
    -0.85
    bread
    -0.71
     cesta
    -0.70
    roof
    -0.68
    明白了
    -0.68
    performance
    -0.67
    ocs
    -0.66
    страции
    -0.66
     malo
    -0.66
    POSITIVE LOGITS
     account
    0.81
    折扣
    0.79
     sécurité
    0.75
     Account
    0.75
    ITES
    0.74
     Rhine
    0.72
     entity
    0.71
     stratigraph
    0.71
    ACCOUNT
    0.71
    COME
    0.70
    Activations Density 0.010%

    No Known Activations