© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17299
    Prev
    Next
    INDEX
    Explanations

    reporting on updates

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

    reporting observations or outcomes

    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
     Нужно
    0.66
     Natürlich
    0.59
    לים
    0.58
     detainees
    0.57
     Необходимо
    0.57
     дороже
    0.57
    т
    0.57
    ка
    0.57
    тели
    0.57
     amines
    0.57
    POSITIVE LOGITS
    Report
    1.45
     Report
    1.31
    Reporting
    1.26
    report
    1.25
     Reporting
    1.24
    Reports
    1.20
     report
    1.18
    REPORT
    1.18
    reports
    1.15
    报告
    1.13
    Activations Density 0.058%

    No Known Activations