© 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. 256672
    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
    eers
    0.47
    deformation
    0.47
    塑
    0.46
     exchangers
    0.45
    Ӏо
    0.44
    る
    0.43
    先進
    0.43
     suspects
    0.42
    刂
    0.42
    plers
    0.42
    POSITIVE LOGITS
     usan
    0.52
     inicio
    0.47
    ijos
    0.47
    ,#
    0.47
     segundo
    0.46
    بود
    0.45
     Guarda
    0.45
    idikan
    0.45
    ,<
    0.45
     desplazamiento
    0.44
    Activations Density 0.002%

    No Known Activations