© 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. 70679
    Prev
    Next
    INDEX
    Explanations

    references to the past

    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
     postwar
    -1.00
    Algérie
    -0.95
    setP
    -0.90
     frow
    -0.89
    șit
    -0.88
     itong
    -0.87
     yow
    -0.86
    上有
    -0.84
     iri
    -0.84
    !\!\
    -0.83
    POSITIVE LOGITS
     now
    1.37
     when
    1.34
     ago
    1.31
     давно
    1.31
     still
    1.26
     then
    1.16
     когда
    1.12
     months
    1.11
     dated
    1.11
    badan
    1.10
    Activations Density 0.059%

    No Known Activations