© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3251
    Prev
    Next
    INDEX
    Explanations

    overfitting in models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
    h
    0.82
    f
    0.76
    te
    0.74
     teeming
    0.70
    v
    0.69
    om
    0.68
    ay
    0.68
     astrophysics
    0.66
     microbiological
    0.64
     etiquette
    0.62
    POSITIVE LOGITS
    L
    0.77
    ↵↵
    0.71
    Senate
    0.65
    Summer
    0.64
    ...+
    0.64
    0.64
    لة
    0.63
    יות
    0.63
    Senator
    0.63
    ="
    0.61
    Activations Density 0.002%

    No Known Activations