© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3082
    Prev
    Next
    INDEX
    Explanations

    automatically selling/buying

    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
    Negative Logits
     enormes
    0.39
    :
    0.37
     przede
    0.35
     ogrom
    0.34
     genomes
    0.33
     unquestionably
    0.33
     decenas
    0.32
     –
    0.32
     quintessential
    0.32
    两大
    0.32
    POSITIVE LOGITS
     eventuali
    0.36
    <unused988>
    0.35
    某些
    0.33
     ചെറിയ
    0.33
    硋
    0.32
     условии
    0.31
     некоторые
    0.31
    लिप
    0.31
     কিছুটা
    0.31
    ทำให้
    0.31
    Activations Density 1.438%

    No Known Activations