© 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. 109531
    Prev
    Next
    INDEX
    Explanations

    technical and place names like municipality

    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
     propósito
    -0.66
     versteht
    -0.65
    tifs
    -0.65
    ➰
    -0.65
     anche
    -0.65
    𝙡
    -0.64
     Gebrauch
    -0.63
    clearing
    -0.63
    BufferSize
    -0.63
     cualidades
    -0.63
    POSITIVE LOGITS
    erende
    0.77
    miede
    0.75
    anyak
    0.73
    Provincia
    0.72
     Provincia
    0.71
    ilar
    0.69
     heli
    0.69
     functor
    0.68
    omin
    0.68
    片
    0.68
    Activations Density 0.063%

    No Known Activations