© 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. 104314
    Prev
    Next
    INDEX
    Explanations

    timestamps and durations

    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
    vertebrates
    -1.73
    vertebrate
    -1.63
     in
    -1.63
    ositol
    -1.58
     Aéroport
    -1.56
     Februari
    -1.55
    vertible
    -1.53
    🐶
    -1.52
     that
    -1.52
     persil
    -1.52
    POSITIVE LOGITS
     myriad
    1.45
     различ
    1.44
    u
    1.42
    匆
    1.38
     letzten
    1.38
     overarching
    1.38
     mehreren
    1.38
    ar
    1.35
     verschiedenen
    1.33
      
    1.31
    Activations Density 0.003%

    No Known Activations