© 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. 41-GEMMASCOPE-2-RES-262K
    7. 4938
    Prev
    Next
    INDEX
    Explanations

    larger or bigger

    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_all/layer_41_width_262k_l0_big
    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
     lightness
    0.49
     सिंपली
    0.44
     simplicity
    0.43
     brilliantly
    0.43
     innumerable
    0.43
     freshness
    0.42
     nominally
    0.42
    蝿
    0.42
     igualmente
    0.42
     simplified
    0.42
    POSITIVE LOGITS
     larger
    1.16
     bigger
    1.12
     Larger
    1.05
    larger
    0.98
    bigger
    0.97
     본격
    0.93
     Bigger
    0.92
     größeren
    0.91
    本格
    0.91
     longer
    0.90
    Activations Density 0.003%

    No Known Activations