© 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. 22788
    Prev
    Next
    INDEX
    Explanations

    monsters, undead, regions

    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
     bombe
    -1.36
     departement
    -1.35
     guir
    -1.35
     SPAIN
    -1.34
     Theologie
    -1.31
     gitt
    -1.30
     palme
    -1.30
     uruguay
    -1.30
     solde
    -1.29
     revisor
    -1.27
    POSITIVE LOGITS
     obtenido
    1.18
     emprender
    1.13
     producido
    1.13
     comparação
    1.13
    </strong>
    1.12
    是吗
    1.10
     propuesto
    1.09
    过多
    1.09
     using
    1.04
     changing
    1.04
    Activations Density 0.020%

    No Known Activations