© 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. 10-GEMMASCOPE-RES-131K
    7. 123642
    Prev
    Next
    INDEX
    Explanations

    asking hypothetical questions

    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_10/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
     abger
    -1.73
    am
    -1.68
     must
    -1.57
     antes
    -1.57
     каждой
    -1.51
     quien
    -1.50
     who
    -1.48
     heath
    -1.47
    によって
    -1.45
    谁
    -1.45
    POSITIVE LOGITS
     pochette
    1.59
    ことがあります
    1.57
    трите
    1.55
     苹果
    1.48
     vitrine
    1.44
     dikt
    1.41
     broderie
    1.40
     maquillage
    1.39
     mera
    1.38
     canapé
    1.38
    Activations Density 0.010%

    No Known Activations