© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63620
    Prev
    Next
    INDEX
    Explanations

    Candidatus species

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

    This neuron detects scientific taxonomic names and classifications, particularly bacterial and microbial species names.

    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
    羰
    -0.83
    Erreferentziak
    -0.77
     dried
    -0.77
     metabolites
    -0.77
    ッポン
    -0.76
    向
    -0.76
    getResource
    -0.73
     Professor
    -0.73
    ttet
    -0.73
    Галерея
    -0.71
    POSITIVE LOGITS
     Objection
    0.81
    谩
    0.79
     obsahuje
    0.78
     reads
    0.76
    detek
    0.73
     proteção
    0.73
    depuis
    0.73
    sudoku
    0.72
    ߛ
    0.71
     clone
    0.71
    Activations Density 0.120%

    No Known Activations