© 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. 81272
    Prev
    Next
    INDEX
    Explanations

    controllers and application components

    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
     bula
    -0.84
    °/
    -0.84
     naa
    -0.84
    叼
    -0.82
    चना
    -0.82
    équipe
    -0.81
     sentiers
    -0.81
     TOO
    -0.80
    Coupe
    -0.79
     ラック
    -0.78
    POSITIVE LOGITS
     và
    0.99
     même
    0.94
    Ȼ
    0.92
    onos
    0.89
    ViewController
    0.88
    :"",
    0.84
    ielen
    0.83
     còn
    0.82
    actment
    0.81
     Europy
    0.80
    Activations Density 0.043%

    No Known Activations