© 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. 22-GEMMASCOPE-RES-131K
    7. 32658
    Prev
    Next
    INDEX
    Explanations

    lab or laboratory

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

    URLs or web addresses containing "lab" or "labs" domains.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ญี่ป
    -3.19
    谖
    -3.06
     dieß
    -2.97
    摃
    -2.80
    腚
    -2.80
    罽
    -2.72
     จาก
    -2.72
    lgari
    -2.69
    鹮
    -2.67
    瑨
    -2.66
    POSITIVE LOGITS
    1
    3.59
    9
    3.45
    \
    3.38
    2
    3.38
    )
    3.34
    8
    3.17
    -
    3.08
    *
    2.94
    3
    2.94
    7
    2.89
    Activations Density 0.012%

    No Known Activations