© 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. 90594
    Prev
    Next
    INDEX
    Explanations

    current topics and issues

    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
    ÁN
    -1.03
    purpose
    -0.98
    enment
    -0.91
    вна
    -0.90
    FieldDescriptor
    -0.90
    anza
    -0.90
    ếp
    -0.89
    setType
    -0.87
    MarshalTo
    -0.86
    tembre
    -0.85
    POSITIVE LOGITS
     topics
    2.52
     timely
    2.30
     current
    2.28
     topical
    2.27
     relevant
    2.17
     issues
    1.92
     актуаль
    1.92
     contemporary
    1.68
     aktu
    1.66
     pertinent
    1.66
    Activations Density 0.081%

    No Known Activations