© 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. 60356
    Prev
    Next
    INDEX
    Explanations

    counterparts, colleagues, predecessors

    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
     another
    -1.26
     другой
    -1.16
     autre
    -1.08
    另一个
    -1.04
    另一
    -1.04
    Дру
    -1.01
    another
    -0.99
     pharmacies
    -0.97
     GPUs
    -0.96
    ikas
    -0.94
    POSITIVE LOGITS
     counterparts
    1.34
     peers
    1.24
     contemporaries
    1.10
     predecessors
    1.03
     competitors
    0.94
     brethren
    0.90
    peers
    0.90
    になったら
    0.87
     brothers
    0.84
     colleagues
    0.82
    Activations Density 0.048%

    No Known Activations