© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 256477
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    넣
    0.48
    の話
    0.48
    蔫
    0.48
     جد
    0.47
    :|
    0.47
    특별시
    0.46
     있었
    0.46
    ็จ
    0.46
    장
    0.45
    ື່
    0.45
    POSITIVE LOGITS
     zahlreichen
    0.48
    nek
    0.43
     variedades
    0.43
     perpetrators
    0.43
     centena
    0.43
     politici
    0.42
     zahlreiche
    0.42
     aren
    0.42
     diferenciales
    0.41
     ergonom
    0.41
    Activations Density 0.000%

    No Known Activations