© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102827
    Prev
    Next
    INDEX
    Explanations

    java package names

    np_acts-logits-general · gemini-2.5-flash-lite

    line breaks and indentation in code (whitespace at the start of new lines).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    奁
    -1.52
     that
    -1.50
     également
    -1.45
    élène
    -1.45
     también
    -1.42
    älde
    -1.37
     triko
    -1.36
     to
    -1.36
    atalos
    -1.34
    боры
    -1.30
    POSITIVE LOGITS
    They
    1.69
     after
    1.55
     should
    1.49
     we
    1.47
    他們
    1.45
     had
    1.32
    Melhor
    1.31
    .
    1.31
    登记
    1.30
    有两
    1.29
    Activations Density 0.030%

    No Known Activations