© 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. 12532
    Prev
    Next
    INDEX
    Explanations

    simultaneously or contrastingly

    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
    jön
    -1.00
     rather
    -0.99
     previously
    -0.98
    previously
    -0.93
    dale
    -0.85
    definitely
    -0.84
    formerly
    -0.84
    твори
    -0.83
     niestety
    -0.82
     افتراض
    -0.81
    POSITIVE LOGITS
     simultaneously
    1.75
     одновременно
    1.54
    simult
    1.43
    同時に
    1.41
     Simultaneously
    1.30
     simultaneous
    1.29
     jednocześnie
    1.24
    同时
    1.24
     zároveň
    1.23
     also
    1.19
    Activations Density 0.032%

    No Known Activations