© 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. 258391
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    +
    0.52
    urious
    0.51
    在你
    0.50
    ar
    0.50
    ip
    0.48
    )},
    0.45
    iphy
    0.45
    _
    0.45
    ichten
    0.45
    保证
    0.45
    POSITIVE LOGITS
     sintomi
    0.51
     Ancak
    0.50
     ಮ
    0.50
     riforma
    0.49
    サッカー
    0.46
     gloom
    0.46
    銠
    0.46
     devem
    0.46
     progrès
    0.46
    ່ມ
    0.46
    Activations Density 0.000%

    No Known Activations