© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66298
    Prev
    Next
    INDEX
    Explanations

    programming and scripting terms

    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
     swoim
    -0.75
    epel
    -0.71
    cinnati
    -0.71
     tachy
    -0.70
    ֵ
    -0.69
     cartão
    -0.68
    maxValue
    -0.68
    angulaire
    -0.68
     suoi
    -0.67
    しさ
    -0.67
    POSITIVE LOGITS
     Oakley
    0.85
    :=
    0.81
     Mask
    0.72
     Nand
    0.71
     piden
    0.70
     quotidienne
    0.69
     Sock
    0.69
    vironment
    0.69
    day
    0.69
    ictionary
    0.68
    Activations Density 0.080%

    No Known Activations