© 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. 34-GEMMASCOPE-RES-131K
    7. 58563
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    你們
    -1.04
     Imperio
    -0.93
    anym
    -0.91
     échelle
    -0.91
    tront
    -0.90
    蟶
    -0.90
     cerro
    -0.90
    彈
    -0.89
    RUS
    -0.88
     TERR
    -0.88
    POSITIVE LOGITS
     OGSÅ
    0.88
    LECTIONS
    0.79
     Hu
    0.79
    ùm
    0.79
     as
    0.78
     involving
    0.78
     Jok
    0.77
     after
    0.77
    注重
    0.77
     predominant
    0.76
    Activations Density 0.000%

    No Known Activations