© 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. 58342
    Prev
    Next
    INDEX
    Explanations

    3D technology

    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_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
     indiví
    -1.23
     solteiro
    -1.20
     sujeito
    -1.05
     senhor
    -0.94
    那时
    -0.94
     juiz
    -0.93
    の説明
    -0.92
     veículo
    -0.92
     fuimos
    -0.91
     moletom
    -0.91
    POSITIVE LOGITS
    ood
    1.03
     modeling
    1.01
    EXPERIENCE
    0.99
    Secure
    0.98
    Connexion
    0.95
     NAND
    0.93
     effect
    0.91
     rendering
    0.87
    connexion
    0.87
    SBS
    0.84
    Activations Density 0.030%

    No Known Activations