© 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. 34-GEMMASCOPE-RES-131K
    7. 84048
    Prev
    Next
    INDEX
    Explanations

    species enumeration

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

    scientific and botanical terminology related to plant species and taxonomy.

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

    This neuron fires on botanical/scientific Latin terms—especially genus, species, and publication names used in plant taxonomy.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    FEL
    -0.79
     PROC
    -0.75
     skul
    -0.73
     alimentation
    -0.73
     Audible
    -0.70
    ৌ
    -0.69
    لهم
    -0.69
     scul
    -0.69
     MIST
    -0.69
     theolog
    -0.68
    POSITIVE LOGITS
     vouchers
    0.94
     sheet
    0.88
     herb
    0.85
    herb
    0.81
    ijer
    0.80
    typ
    0.78
     Sheet
    0.78
    hashi
    0.78
     Flora
    0.77
     sheets
    0.76
    Activations Density 0.032%

    No Known Activations