© 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. 33395
    Prev
    Next
    INDEX
    Explanations

    church parts and 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
    fahrts
    -0.93
    attare
    -0.91
     deities
    -0.79
    Inspec
    -0.77
    itemName
    -0.76
    piele
    -0.74
    internalType
    -0.74
     pouvons
    -0.73
    čky
    -0.73
     extradition
    -0.73
    POSITIVE LOGITS
     nave
    1.49
     chancel
    1.02
     choir
    1.02
     tran
    1.00
     Nave
    0.94
    Nave
    0.93
     неф
    0.92
    nave
    0.91
     Chan
    0.88
    choir
    0.80
    Activations Density 0.021%

    No Known Activations