© 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. 244633
    Prev
    Next
    INDEX
    Explanations

    helpful info

    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
    を用いる
    0.51
     MA
    0.47
    toByteArray
    0.47
     Akk
    0.45
    生成的
    0.45
    自定义
    0.44
    etaan
    0.43
    )*(
    0.42
    credentials
    0.42
    ворю
    0.42
    POSITIVE LOGITS
     них
    0.51
    Statuses
    0.47
    拉斯
    0.45
     उन्‍होंने
    0.44
    Multimedia
    0.43
     ними
    0.43
    ené
    0.42
     मरम्मत
    0.42
     falta
    0.42
     ресурсов
    0.41
    Activations Density 0.001%

    No Known Activations