© 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. 50400
    Prev
    Next
    INDEX
    Explanations

    permissions and

    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
     Pests
    -0.70
    VALUE
    -0.70
    شار
    -0.69
    serving
    -0.68
     EEA
    -0.68
    管理
    -0.68
     квадра
    -0.67
    Band
    -0.67
     DSL
    -0.66
     anglo
    -0.66
    POSITIVE LOGITS
     нещо
    0.73
    bookstore
    0.71
     revés
    0.68
     probabilities
    0.67
    checkFor
    0.66
     przy
    0.65
    acal
    0.65
     ganhar
    0.64
    sbs
    0.64
     vice
    0.63
    Activations Density 0.048%

    No Known Activations