© 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. 50169
    Prev
    Next
    INDEX
    Explanations

    legume pods

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

    Latin names of plant species.

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

    The neuron strongly activates on the structured numeric and punctuation patterns typical of scientific taxonomy and reference notation (e.g. parenthesized genus–species lines, numbered citations, and related symbols).

    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
    otoro
    -0.77
     Plymouth
    -0.75
    QJ
    -0.71
     receptacle
    -0.69
    Plymouth
    -0.69
    ждён
    -0.69
    扩大
    -0.68
     setTitle
    -0.68
    scription
    -0.68
    рын
    -0.67
    POSITIVE LOGITS
     pods
    1.51
     pod
    1.30
     Acacia
    1.22
     legume
    1.19
     acacia
    1.13
     legumes
    1.06
     Pods
    1.02
    pods
    1.00
    pod
    0.97
     Pod
    0.91
    Activations Density 0.034%

    No Known Activations