© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 317
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FS
    1.15
    FD
    1.03
     FD
    1.01
     FS
    1.00
    F
    0.99
    fs
    0.99
     F
    0.93
    FC
    0.92
    Fs
    0.91
    Fed
    0.88
    POSITIVE LOGITS
     limousine
    1.00
     RIM
    0.95
    imine
    0.94
     Zimmermann
    0.89
    RIM
    0.86
    ylamine
    0.85
     Bim
    0.85
     limo
    0.84
     Akin
    0.84
    oyin
    0.83
    Activations Density 5.959%

    No Known Activations