© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34050
    Prev
    Next
    INDEX
    Explanations

    protozoan parasite

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

    nouns that represent organized institutions, facilities, or groups like parasite, camp, company, temple, and tournament.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on the single key content noun that names the main subject or topic of a section or document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
     empêcher
    -1.38
     و
    -1.30
    และ
    -1.29
     コミック
    -1.28
     マンガ
    -1.24
     destinés
    -1.23
     protéger
    -1.22
     フィギュア
    -1.21
    หรือ
    -1.21
     получить
    -1.21
    POSITIVE LOGITS
     Gå
    1.36
     pacto
    1.29
    迳
    1.27
     柱
    1.23
    美国的
    1.19
    中には
    1.17
    竟然是
    1.14
    两者
    1.14
     Nå
    1.11
     Février
    1.10
    Activations Density 0.632%

    No Known Activations