© 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. 255344
    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
     dictatorship
    0.46
    颛
    0.46
    כו
    0.46
    מו
    0.46
    Issued
    0.46
    COMMAND
    0.45
    Cause
    0.42
    וד
    0.41
    நுட்ப
    0.41
     আসবেন
    0.41
    POSITIVE LOGITS
    ays
    0.54
    ị
    0.52
    yl
    0.51
    alui
    0.50
    égi
    0.48
     पा
    0.47
     ei
    0.47
    ras
    0.46
     रही
    0.46
    oli
    0.46
    Activations Density 0.001%

    No Known Activations