© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 32374
    Prev
    Next
    INDEX
    Explanations

    units and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    测量
    0.46
     Measuring
    0.43
     decimal
    0.43
    📏
    0.42
     বিধ
    0.42
     measured
    0.40
    olius
    0.40
     Convert
    0.39
    Measuring
    0.39
     өл
    0.38
    POSITIVE LOGITS
    year
    0.43
    years
    0.42
     énerg
    0.42
    Hz
    0.39
     bimodule
    0.39
    }/\
    0.39
    peasants
    0.39
     tahun
    0.39
    ゴ
    0.39
    suffix
    0.39
    Activations Density 0.009%

    No Known Activations