© 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. 75692
    Prev
    Next
    INDEX
    Explanations

    November 29

    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
     the
    -1.23
     coussin
    -1.19
     Ejército
    -1.15
     Automó
    -1.13
     linge
    -1.08
     ۱۴
    -1.08
     conseillers
    -1.08
     earlier
    -1.07
     inspiradoras
    -1.07
     couvercle
    -1.05
    POSITIVE LOGITS
     homicidio
    1.27
    Boxscore
    1.23
     Поэтому
    1.19
     decap
    1.10
     Deshalb
    1.02
    ərbaycan
    1.00
    зим
    0.98
    argout
    0.98
     เน
    0.96
    是非常
    0.96
    Activations Density 0.092%

    No Known Activations