© 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. 118219
    Prev
    Next
    INDEX
    Explanations

    numbers and specific codes

    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
     which
    -1.02
     or
    -0.98
     then
    -0.96
     sodio
    -0.94
     says
    -0.87
     said
    -0.84
    一边
    -0.81
     Winners
    -0.81
     understood
    -0.80
    ('\
    -0.80
    POSITIVE LOGITS
    Kategorie
    1.08
    久しぶりに
    1.07
     acabamento
    1.02
    nonatomic
    1.02
    Heute
    1.02
     espoir
    1.00
    久しぶりの
    0.99
     acela
    0.98
    Erfahrung
    0.97
    Последние
    0.97
    Activations Density 0.001%

    No Known Activations