© 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. 254339
    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
     viszont
    0.48
    ۇل
    0.46
    OrCreate
    0.46
    สามารถ
    0.43
    棗
    0.43
    க்கொ
    0.43
     sagen
    0.42
    кратно
    0.42
     sorgen
    0.42
     saber
    0.41
    POSITIVE LOGITS
     그는
    0.53
    ifères
    0.47
    他对
    0.47
    Aer
    0.47
    ila
    0.46
     વ્યવ
    0.46
    λημα
    0.46
    栏
    0.45
     earnestly
    0.45
    aer
    0.44
    Activations Density 0.001%

    No Known Activations