© 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. 31-GEMMASCOPE-2-RES-262K
    7. 29268
    Prev
    Next
    INDEX
    Explanations

    Published dates and numbers

    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_31_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
     subsequent
    0.35
     первая
    0.35
    两者
    0.34
    هی
    0.33
     Artin
    0.33
    <start_of_image>
    0.32
    最初
    0.32
     LCS
    0.32
    段
    0.32
    ிலேயே
    0.32
    POSITIVE LOGITS
    ຼ
    0.38
    tene
    0.36
    မ္
    0.36
    subscriber
    0.35
    Likewise
    0.35
     tidligere
    0.35
     asimismo
    0.35
     "'.$
    0.35
    軲
    0.35
    ญิง
    0.34
    Activations Density 0.019%

    No Known Activations