© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83064
    Prev
    Next
    INDEX
    Explanations

    initiating actions and collaborations

    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
    "/>
    
    -1.11
     kalender
    -1.09
     trattano
    -1.08
     összefoglaló
    -1.03
     radikal
    -1.02
    ܖ
    -1.02
     всички
    -1.00
    になるので
    -0.95
     semblent
    -0.94
     seraient
    -0.93
    POSITIVE LOGITS
     created
    1.73
     host
    1.34
     worked
    1.33
     working
    1.30
     work
    1.28
     hire
    1.28
     conduct
    1.25
     hosting
    1.25
     participate
    1.24
     developed
    1.20
    Activations Density 0.047%

    No Known Activations