© 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. 252808
    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
     रोगियों
    0.52
    悹
    0.52
    ánea
    0.52
     пациентов
    0.50
    さまざ
    0.50
     ሰዎች
    0.48
    季节
    0.48
    絟
    0.46
     جوسینو
    0.46
     менее
    0.46
    POSITIVE LOGITS
     Prefeitura
    0.47
     deftly
    0.44
     invent
    0.43
     Botox
    0.43
     eles
    0.43
    Letters
    0.41
    (/[
    0.41
     deu
    0.40
     ofens
    0.40
     Construct
    0.39
    Activations Density 0.001%

    No Known Activations