© 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. 10-GEMMASCOPE-RES-131K
    7. 101142
    Prev
    Next
    INDEX
    Explanations

    animals, especially mammals and reptiles

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

    animal names, particularly mammals, reptiles, and amphibians.

    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_10/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
     enorme
    -1.38
    </u>
    -1.33
    etto
    -1.32
    遢
    -1.30
     eaux
    -1.30
     netto
    -1.28
     TRY
    -1.28
     )}
    -1.27
    ものの
    -1.27
    饮料
    -1.26
    POSITIVE LOGITS
     his
    1.39
     six
    1.36
    鷺
    1.34
     nuovamente
    1.33
    jaqueta
    1.33
    riscoll
    1.32
    carhartt
    1.32
     Tämä
    1.28
    民宿
    1.27
    钜
    1.27
    Activations Density 0.067%

    No Known Activations