© 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. 82635
    Prev
    Next
    INDEX
    Explanations

    code or license text

    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
     contacts
    -0.66
     respondió
    -0.66
    lois
    -0.66
    SaveChangesAsync
    -0.65
     ochron
    -0.64
    缮
    -0.63
     genoemd
    -0.63
     virginity
    -0.62
     Transitional
    -0.62
     Front
    -0.62
    POSITIVE LOGITS
     avocado
    0.71
     ditemp
    0.70
     椅子
    0.70
    اسف
    0.69
     respiratory
    0.69
     koh
    0.67
     hauts
    0.67
     pengu
    0.66
     kuat
    0.64
    accessor
    0.64
    Activations Density 0.089%

    No Known Activations