© 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. 102566
    Prev
    Next
    INDEX
    Explanations

    ras prefixes and their followings

    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
    Wik
    -0.84
    нему
    -0.83
    takers
    -0.79
    giving
    -0.79
     tenda
    -0.78
     dolce
    -0.75
    唐揚げ
    -0.75
    farer
    -0.73
     другу
    -0.73
    urable
    -0.73
    POSITIVE LOGITS
     рас
    1.10
     Tight
    0.88
     pasada
    0.81
     сначала
    0.80
     расс
    0.79
     дослі
    0.78
     reír
    0.78
    ふん
    0.78
     contamos
    0.77
     enquanto
    0.76
    Activations Density 0.012%

    No Known Activations