© 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. 152596
    Prev
    Next
    INDEX
    Explanations

    word or phrase followed by specific nouns/verbs

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

    emergence of generative models

    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
    薇
    0.46
     ලි
    0.46
    ล์
    0.42
    윌
    0.42
    <0xB6>
    0.40
    아이
    0.40
     Alina
    0.40
     Inglaterra
    0.40
     unut
    0.39
    gahan
    0.39
    POSITIVE LOGITS
    s
    0.50
     gering
    0.49
     vermeiden
    0.49
     sage
    0.49
     দুর্ভিক্ষ
    0.48
     холоди
    0.48
    বেদন
    0.46
    sage
    0.46
     impervious
    0.46
     anabolic
    0.46
    Activations Density 0.000%

    No Known Activations