© 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. 253
    Prev
    Next
    INDEX
    Explanations

    legal conditions or software clauses

    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
    Сто
    -0.93
    tempat
    -0.90
     januari
    -0.87
    antaranya
    -0.85
     waaronder
    -0.84
     Tipo
    -0.84
    okohama
    -0.83
    uksessa
    -0.82
    Только
    -0.82
     тільки
    -0.81
    POSITIVE LOGITS
     ajudá
    1.30
     helpful
    1.20
     help
    1.16
     helps
    1.09
     each
    1.02
     ativar
    1.00
     shows
    0.99
     benefit
    0.96
    至今
    0.96
     fotbal
    0.95
    Activations Density 0.002%

    No Known Activations