© 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. 10-GEMMASCOPE-RES-131K
    4. 42744
    Prev
    Next
    INDEX
    Explanations

    replicates, experiments, sets. parallel

    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_10/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
     would
    -2.14
     is
    -1.66
     their
    -1.60
     could
    -1.53
     There
    -1.48
     has
    -1.38
    ulihan
    -1.38
     will
    -1.37
     might
    -1.36
     what
    -1.35
    POSITIVE LOGITS
     erhi
    1.55
     guapa
    1.44
     naszych
    1.41
     versions
    1.41
    Groeten
    1.41
     Logement
    1.40
     autoestima
    1.39
    Groet
    1.35
    繽
    1.34
     захворю
    1.33
    Activations Density 0.044%

    No Known Activations