© 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. 116729
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    тата
    -0.80
    ಐ
    -0.79
    jande
    -0.79
     minus
    -0.77
     Grimes
    -0.77
     palsu
    -0.76
     jedynie
    -0.75
    ideal
    -0.75
    useum
    -0.75
    agos
    -0.74
    POSITIVE LOGITS
    🚭
    0.79
     nonnegative
    0.76
     positive
    0.76
     Coolidge
    0.75
     TCU
    0.71
     welcomes
    0.70
     hubiera
    0.69
     skeletons
    0.69
    ります
    0.68
    Naissance
    0.68
    Activations Density 0.100%

    No Known Activations