© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20583
    Prev
    Next
    INDEX
    Explanations

    children and their circumstances

    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
     offer
    -2.95
    or
    -2.88
     humeur
    -2.80
     become
    -2.44
     et
    -2.42
    to
    -2.34
     has
    -2.30
    }$
    -2.30
    are
    -2.30
     that
    -2.30
    POSITIVE LOGITS
    淠
    3.03
    </td>
    3.02
    </i>
    2.95
     褲
    2.77
     häufiger
    2.73
     تھا
    2.66
    "">
    2.63
    ⬮
    2.59
    \">\
    2.58
    趼
    2.56
    Activations Density 0.028%

    No Known Activations