© 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. 54531
    Prev
    Next
    INDEX
    Explanations

    graph theory contexts (V, E, G)

    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
     antworten
    -1.01
     anderen
    -0.99
     angene
    -0.97
    寝る
    -0.97
     hipótesis
    -0.93
     penjelasan
    -0.93
    你也
    -0.93
     nth
    -0.92
     menuju
    -0.90
    vrons
    -0.90
    POSITIVE LOGITS
    场比赛
    1.05
    ','.
    0.98
     imobili
    0.97
     controla
    0.96
    这让
    0.96
    formin
    0.95
     sapi
    0.93
    梣
    0.92
     Presidencia
    0.92
     cenário
    0.91
    Activations Density 0.041%

    No Known Activations