© 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. 72604
    Prev
    Next
    INDEX
    Explanations

    number of children

    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
    ↵
    -1.66
     to
    -1.42
    找到了
    -1.16
    liğini
    -1.15
     pourrait
    -1.15
    を終
    -1.15
    <i>
    -1.12
     position
    -1.11
    側の
    -1.11
     leading
    -1.09
    POSITIVE LOGITS
    Those
    1.51
    When
    1.32
     two
    1.30
     heridas
    1.29
    去年
    1.29
     children
    1.28
    האם
    1.28
    英國
    1.27
     those
    1.27
     kids
    1.27
    Activations Density 0.064%

    No Known Activations