© 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. 78156
    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
     bättre
    -0.94
     besonderen
    -0.90
    :"",
    -0.86
    想要
    -0.85
     dessutom
    -0.84
    achev
    -0.84
     båda
    -0.83
    📘
    -0.82
     normalen
    -0.82
     äls
    -0.82
    POSITIVE LOGITS
     весьма
    0.88
     외
    0.85
     решила
    0.81
    sibles
    0.79
    かも知
    0.78
    筋
    0.78
     twos
    0.76
     hafta
    0.75
    洒落
    0.75
     xám
    0.73
    Activations Density 0.000%

    No Known Activations