© 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. 10-GEMMASCOPE-RES-131K
    7. 57540
    Prev
    Next
    INDEX
    Explanations

    Commando adventure

    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_10/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
     our
    -1.84
     Secrétaire
    -1.61
    jectile
    -1.53
    蒾
    -1.52
     stratég
    -1.52
    Décès
    -1.52
     parution
    -1.51
    嘁
    -1.48
     propuestas
    -1.48
     Saludos
    -1.47
    POSITIVE LOGITS
    the
    1.84
    j
    1.83
    a
    1.69
    k
    1.69
    d
    1.69
    they
    1.68
    s
    1.66
    ll
    1.60
    it
    1.60
          
    1.58
    Activations Density 0.121%

    No Known Activations