© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47431
    Prev
    Next
    INDEX
    Explanations

    connecting and linking routes

    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
     verf
    -0.80
    PONENT
    -0.78
    modb
    -0.77
    ждение
    -0.76
    Conjunto
    -0.74
     Νο
    -0.74
    rijfs
    -0.73
     IconData
    -0.73
    拗
    -0.72
    ╨
    -0.72
    POSITIVE LOGITS
     connecting
    5.69
     connect
    5.47
     connects
    5.16
    connect
    4.66
     Connecting
    4.59
     linking
    4.53
    connecting
    4.53
    Connecting
    4.53
    连接
    4.41
    Connect
    4.22
    Activations Density 0.331%

    No Known Activations