© 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. 93966
    Prev
    Next
    INDEX
    Explanations

    South Australia, Chile, South Africa locations

    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
    ownership
    -0.78
     PDP
    -0.76
    fool
    -0.74
    Retrieval
    -0.72
    lais
    -0.71
     SOCIETY
    -0.70
    rozum
    -0.69
    gambarkan
    -0.68
    Planner
    -0.67
     свадеб
    -0.66
    POSITIVE LOGITS
    幢
    0.72
     opi
    0.71
    gences
    0.69
     cray
    0.68
     порт
    0.67
    obenz
    0.67
     بزن
    0.66
     очередь
    0.66
     Kick
    0.66
     Guin
    0.66
    Activations Density 0.053%

    No Known Activations