© 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. 94246
    Prev
    Next
    INDEX
    Explanations

    appendages growing or protruding

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

    anatomical features of animals and creatures, such as legs, tentacles, eyes, claws, and other body parts.

    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
     Quân
    -0.90
    lorin
    -0.83
     cucharadita
    -0.82
    }{||
    -0.82
    रो
    -0.76
    kiye
    -0.75
    енье
    -0.75
    plers
    -0.75
    ταν
    -0.74
    ᾿
    -0.73
    POSITIVE LOGITS
     retractable
    1.14
     grows
    1.13
     growing
    1.11
     grew
    1.09
    Growing
    1.07
     GROW
    1.03
    growing
    0.99
     protruding
    0.98
     grow
    0.98
    append
    0.94
    Activations Density 0.035%

    No Known Activations