© 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. 70632
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
     the
    -1.92
     their
    -1.77
     our
    -1.62
     which
    -1.59
    ஒ
    -1.56
    Ironically
    -1.55
     perdiendo
    -1.50
    ஊ
    -1.48
    dott
    -1.48
    tanda
    -1.48
    POSITIVE LOGITS
    StoryboardSegue
    1.87
    т
    1.83
    keted
    1.72
    agine
    1.72
     lopez
    1.66
    imetry
    1.66
    ),
    1.66
    ೞ
    1.63
    aneity
    1.62
    AxisAlignment
    1.61
    Activations Density 0.000%

    No Known Activations