© 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. 84379
    Prev
    Next
    INDEX
    Explanations

    level 1

    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
     svært
    -1.23
     poliester
    -1.07
     هفته
    -1.07
    ikkert
    -1.04
     ratusan
    -1.02
    した場合
    -1.02
    两人的
    -1.02
    当时的
    -1.02
     menurun
    -1.01
    这个时候
    -1.00
    POSITIVE LOGITS
     sieben
    1.13
    靱
    1.09
    URLEncoder
    1.06
     Sorgen
    1.04
    )
    1.02
     Nachbar
    1.00
     impacts
    0.99
     Akte
    0.98
     research
    0.98
     cost
    0.98
    Activations Density 0.003%

    No Known Activations