© 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. 34-GEMMASCOPE-RES-131K
    7. 25938
    Prev
    Next
    INDEX
    Explanations

    o' names

    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_34/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
     cosmopolitan
    -0.87
    浄
    -0.84
     桜
    -0.77
     findest
    -0.75
     Tiny
    -0.75
    ギー
    -0.74
     наблюда
    -0.72
    РОВ
    -0.72
     Lister
    -0.72
     suckers
    -0.72
    POSITIVE LOGITS
    ourke
    0.89
     Rossa
    0.75
    μβρίου
    0.71
    ítő
    0.68
    eara
    0.67
     mato
    0.67
    Ciri
    0.66
     Berto
    0.66
    Ici
    0.66
     رای
    0.65
    Activations Density 0.022%

    No Known Activations