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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29104
    Prev
    Next
    INDEX
    Explanations

    species scientific names (P., C., T., S.)

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

    This neuron identifies species abbreviations (P. or C. followed by a species name).

    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
    0
    -2.16
    5
    -1.98
     you
    -1.88
    6
    -1.82
    2
    -1.80
    7
    -1.65
     salão
    -1.63
    leten
    -1.62
    4
    -1.62
    如果
    -1.61
    POSITIVE LOGITS
     that
    1.77
     from
    1.77
    ’
    1.65
    ,
    1.63
     can
    1.52
     and
    1.52
     before
    1.41
     while
    1.41
    ございません
    1.34
     â
    1.31
    Activations Density 0.040%

    No Known Activations