© 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. 22-GEMMASCOPE-RES-131K
    4. 12589
    Prev
    Next
    INDEX
    Explanations

    proper nouns and acronyms

    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
     Transfermarkt
    -1.27
    ﷲ
    -1.27
     {{$
    -1.19
    нимание
    -1.15
    =$(
    -1.13
    IVENESS
    -1.12
    вича
    -1.12
     maintenant
    -1.10
    ANZE
    -1.09
    щению
    -1.09
    POSITIVE LOGITS
    velocityX
    1.06
     няколко
    1.05
    攻擊
    1.04
    思います
    1.03
     and
    1.02
     some
    1.02
     after
    0.99
     вообще
    0.99
     saludable
    0.99
     as
    0.98
    Activations Density 0.001%

    No Known Activations