© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45652
    Prev
    Next
    INDEX
    Explanations

    little girl or boy

    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
    Negative Logits
     arbeta
    -2.16
    nocení
    -1.79
     Humanos
    -1.78
    但这
    -1.77
    ↵↵
    -1.77
     Sociales
    -1.74
    ก่อน
    -1.71
    韞
    -1.70
    𝙃
    -1.70
    ━━
    -1.67
    POSITIVE LOGITS
    3
    2.41
    </i>
    2.06
    8
    2.03
    5
    2.02
    1
    1.95
    7
    1.91
    /
    1.90
    9
    1.73
    6
    1.73
     pleas
    1.64
    Activations Density 0.006%

    No Known Activations