© 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. 28350
    Prev
    Next
    INDEX
    Explanations

    Action verbs and observations

    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
     chua
    -1.06
    ține
    -1.05
     repuesto
    -1.04
     refaire
    -1.00
     llorar
    -0.99
     sustituir
    -0.97
    documentElement
    -0.97
     cães
    -0.95
     encender
    -0.95
     khong
    -0.94
    POSITIVE LOGITS
     it
    2.69
     this
    2.31
     them
    2.02
     in
    1.94
     during
    1.62
     by
    1.52
     from
    1.48
     these
    1.38
     through
    1.35
     это
    1.34
    Activations Density 0.092%

    No Known Activations