© 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. 83805
    Prev
    Next
    INDEX
    Explanations

    rich. As in food, fabric, color, sound, or economic

    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
    킁
    -1.23
     laborales
    -1.20
    icherung
    -1.20
    crites
    -1.20
    entada
    -1.19
     jesteśmy
    -1.19
     sensazione
    -1.16
     بگیر
    -1.15
    的方式
    -1.15
    بيرة
    -1.14
    POSITIVE LOGITS
    </strong>
    1.10
    </h4>
    1.09
     beiden
    1.06
     kado
    1.02
    Crm
    1.00
     narra
    0.99
     eenen
    0.98
     gespe
    0.98
     Batterie
    0.97
    enscha
    0.96
    Activations Density 0.036%

    No Known Activations