© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38864
    Prev
    Next
    INDEX
    Explanations

    numbers and other words

    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
     только
    -1.27
    某些
    -1.16
     никогда
    -1.16
     ersten
    -1.12
     будет
    -1.12
     первый
    -1.10
     solcher
    -1.09
     gebeurt
    -1.09
     должны
    -1.08
     первым
    -1.07
    POSITIVE LOGITS
     other
    4.31
     another
    4.22
     further
    3.94
     more
    3.42
     additional
    3.41
     další
    3.31
     weitere
    3.05
     others
    3.00
     dalších
    2.91
    อีก
    2.89
    Activations Density 0.104%

    No Known Activations