© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62459
    Prev
    Next
    INDEX
    Explanations

    methyl, ethyl, paraffin, dehydration, fixation

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

    chemical compounds and laboratory materials used in scientific or technical procedures.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ิลป
    -0.84
    tenberg
    -0.78
     Вікіпе
    -0.77
     シーズン
    -0.76
    餘
    -0.75
    xtra
    -0.74
    weakSelf
    -0.73
     leather
    -0.72
     domande
    -0.71
    IVEN
    -0.71
    POSITIVE LOGITS
     mounting
    1.24
     mount
    1.00
     Mounting
    0.96
    Mounting
    0.93
    mounting
    0.91
    seal
    0.85
    MOUNT
    0.81
     immersion
    0.77
     media
    0.75
     mounted
    0.73
    Activations Density 0.021%

    No Known Activations