© 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. 60291
    Prev
    Next
    INDEX
    Explanations

    classified ads and responses

    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
     streams
    -0.83
     affrontare
    -0.79
    љено
    -0.77
     със
    -0.75
    viste
    -0.73
     Proper
    -0.72
    mqtt
    -0.71
    鬚
    -0.71
    quido
    -0.71
     realizzare
    -0.71
    POSITIVE LOGITS
     REPLY
    0.94
     Craigslist
    0.93
    Responses
    0.85
     meubles
    0.85
     texte
    0.85
    stuhl
    0.84
     спорт
    0.84
     reply
    0.81
     mobilier
    0.81
    Membrane
    0.81
    Activations Density 0.019%

    No Known Activations