© 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. 162438
    Prev
    Next
    INDEX
    Explanations

    synagogue, cost, rato, database

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

    silicon film

    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
    פל
    0.49
     частей
    0.45
    ("+
    0.44
     kartu
    0.44
    getpath
    0.44
    头的
    0.43
     میک
    0.42
    ността
    0.42
    '/
    0.42
     pomocą
    0.42
    POSITIVE LOGITS
     JESUS
    0.47
    ීය
    0.47
     Biot
    0.46
     Ấ
    0.46
    roasted
    0.46
     Baked
    0.44
     দৌড়ে
    0.44
    })$.
    0.43
     roasted
    0.43
     aika
    0.43
    Activations Density 0.001%

    No Known Activations