© 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. 22-GEMMASCOPE-RES-131K
    7. 74958
    Prev
    Next
    INDEX
    Explanations

    age numbers

    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
     each
    -1.56
     that
    -1.49
     when
    -1.34
    when
    -1.25
     while
    -1.23
     it
    -1.21
     one
    -1.09
     for
    -1.09
     reloadData
    -1.07
    などなど
    -1.05
    POSITIVE LOGITS
     desnuda
    1.25
     antiguos
    1.20
     összefoglal
    1.16
     esclavos
    1.16
     impresionantes
    1.10
    ův
    1.08
     tých
    1.08
     našich
    1.05
     colgante
    1.02
     enemigos
    1.02
    Activations Density 0.029%

    No Known Activations