© 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. 22-GEMMASCOPE-RES-131K
    7. 128310
    Prev
    Next
    INDEX
    Explanations

    code context separators

    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
    styleUrls
    -0.89
    endDate
    -0.88
     matematika
    -0.85
    setArguments
    -0.85
     during
    -0.84
     prayer
    -0.82
    Ngày
    -0.82
     follow
    -0.82
    ależy
    -0.81
    ช่วย
    -0.79
    POSITIVE LOGITS
    corresponding
    1.03
    converted
    1.00
     equivalent
    1.00
    Сю
    0.94
     converted
    0.94
    ほら
    0.94
    Джере
    0.94
    Corresponding
    0.92
    ,;
    0.91
     übertragen
    0.90
    Activations Density 0.058%

    No Known Activations