© 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. 22-GEMMASCOPE-RES-131K
    7. 95679
    Prev
    Next
    INDEX
    Explanations

    maximum and average values

    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_22/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
    rayal
    -0.93
     Beton
    -0.91
     nimmer
    -0.90
     vitale
    -0.89
     گذشت
    -0.89
     hins
    -0.86
    рія
    -0.84
     vecchio
    -0.84
    вец
    -0.84
    といえば
    -0.84
    POSITIVE LOGITS
     there
    1.07
     решил
    0.83
     Complaints
    0.82
     remove
    0.77
    тером
    0.77
     miedo
    0.76
     Threatened
    0.76
     here
    0.73
    總
    0.73
    ellino
    0.72
    Activations Density 0.014%

    No Known Activations