© 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. 93479
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related items

    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
    ölkerung
    -0.83
     assise
    -0.82
    europ
    -0.82
    nancy
    -0.82
     dénon
    -0.80
     olabilir
    -0.79
     остальные
    -0.78
    rachel
    -0.78
    Tito
    -0.77
     Автор
    -0.77
    POSITIVE LOGITS
     its
    1.53
     practitioners
    0.95
    元年
    0.94
     suoi
    0.93
    its
    0.86
     related
    0.84
     people
    0.84
     ketua
    0.81
     jej
    0.81
     by
    0.78
    Activations Density 0.122%

    No Known Activations