© 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. 154218
    Prev
    Next
    INDEX
    Explanations

    citizens and more

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasting rote memorization with learned structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ing
    0.48
    ed
    0.48
    agle
    0.48
    ase
    0.48
    ann
    0.47
    人
    0.47
    lichen
    0.46
    낡
    0.46
    ig
    0.45
    liqu
    0.45
    POSITIVE LOGITS
     utiliz
    0.54
     সুষ্ঠ
    0.53
     මො
    0.53
     naciones
    0.52
     Patric
    0.51
     pudieran
    0.51
     ރ
    0.51
     संस्थ
    0.50
     সকলকে
    0.49
    न्दु
    0.48
    Activations Density 0.000%

    No Known Activations