© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108452
    Prev
    Next
    INDEX
    Explanations

    worms and intestines

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

    scientific names of organisms, particularly taxonomy of invertebrates such as insects, millipedes, and other arthropods.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Sharks
    -0.84
     shark
    -0.83
     собака
    -0.81
     sharks
    -0.78
     Buc
    -0.78
    ұл
    -0.77
     MemoryStream
    -0.77
    dog
    -0.77
     ys
    -0.75
     Stalker
    -0.74
    POSITIVE LOGITS
     worms
    1.91
     worm
    1.82
     Worm
    1.65
    worm
    1.48
    Worm
    1.48
    worms
    1.44
     Worms
    1.42
     castings
    1.40
     earth
    1.30
    Eisen
    1.11
    Activations Density 0.050%

    No Known Activations