© 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. 84527
    Prev
    Next
    INDEX
    Explanations

    numbers and file paths

    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
    Eventually
    -0.88
     modus
    -0.88
    Ouverture
    -0.87
    הח
    -0.86
    ptos
    -0.84
     chacune
    -0.82
    Parks
    -0.81
     fidé
    -0.80
    LECTION
    -0.79
    eventually
    -0.79
    POSITIVE LOGITS
     then
    1.30
     immediately
    1.16
     shortly
    1.16
     further
    1.04
     Immediately
    1.00
     this
    0.99
    紧接着
    0.98
    了一下
    0.97
     few
    0.92
     next
    0.91
    Activations Density 0.024%

    No Known Activations