© 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. 10-GEMMASCOPE-RES-131K
    7. 48259
    Prev
    Next
    INDEX
    Explanations

    technical command names

    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_10/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
    ﮨ
    -1.45
     obicei
    -1.41
    när
    -1.40
    ほうがいい
    -1.38
    
    -1.36
    capulco
    -1.35
     collega
    -1.35
     freddo
    -1.35
    phrodite
    -1.34
     môžu
    -1.34
    POSITIVE LOGITS
     there
    1.96
     by
    1.44
     a
    1.41
    There
    1.34
     you
    1.34
     A
    1.34
    ちなみに
    1.30
     something
    1.30
    //
    1.28
     некото
    1.28
    Activations Density 0.133%

    No Known Activations