© 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. 154531
    Prev
    Next
    INDEX
    Explanations

    performance time capacity utilization

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

    identifying and understanding languages

    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
    Tucker
    0.53
    张
    0.52
    Do
    0.46
    Fetch
    0.46
    BufOffset
    0.46
    Zhang
    0.46
    ૃહ
    0.46
    中国
    0.45
    后期
    0.45
     张
    0.44
    POSITIVE LOGITS
     সাক্ষ
    0.47
    <unused64>
    0.46
    ybės
    0.44
    ību
    0.44
     दरम्यान
    0.43
     chứng
    0.43
     автоматтары
    0.43
     দিনের
    0.43
     Ethyl
    0.42
     দিন
    0.42
    Activations Density 0.001%

    No Known Activations