© 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. 259095
    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
    freien
    0.54
    ے
    0.48
    verting
    0.48
     игровой
    0.47
    mlabeledtr
    0.46
    bble
    0.46
    ārt
    0.46
    ocycl
    0.46
    egal
    0.45
    essori
    0.44
    POSITIVE LOGITS
     emplea
    0.50
     destinado
    0.46
     employ
    0.46
    由于
    0.45
     DEPARTMENT
    0.44
     punish
    0.44
    罰
    0.44
     filhos
    0.44
     relaciona
    0.44
     fire
    0.43
    Activations Density 0.001%

    No Known Activations