© 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. 68525
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
     السياس
    -1.67
     schmeckt
    -1.16
     وزار
    -1.12
     disso
    -1.09
    అ
    -1.09
     边框
    -1.08
     barcel
    -1.07
    హ
    -1.07
     کردیم
    -1.05
     Asoci
    -1.03
    POSITIVE LOGITS
     you
    1.41
     also
    1.18
     すぎ
    1.17
     eventually
    1.16
     your
    1.16
     Forum
    1.14
    reply
    1.13
     I
    1.13
     comunque
    1.11
    olding
    1.10
    Activations Density 0.128%

    No Known Activations