© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42586
    Prev
    Next
    INDEX
    Explanations

    willow and poplar trees

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

    names of trees or plants, particularly varieties of willow, poplar, and birch.

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

    The neuron fires on mentions of specific tree (plant) species names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    }$
    -2.61
    In
    -2.36
     оборудования
    -2.20
     hoher
    -2.09
     ensures
    -2.09
    "}}>
    -2.05
    te
    -1.98
    er
    -1.95
     comprises
    -1.93
     oscu
    -1.92
    POSITIVE LOGITS
    s
    2.19
    邶
    2.11
    “
    2.06
    neſs
    2.06
     για
    2.00
     Anſ
    1.97
    </h3>
    1.95
    垻
    1.91
    迓
    1.89
     rangs
    1.88
    Activations Density 0.005%

    No Known Activations