© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108862
    Prev
    Next
    INDEX
    Explanations

    aromatic compounds and therapy

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

    chemical and scientific terms related to aromatic compounds.

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

    The neuron fires on the character sequence “aro” (e.g. in AroClor, aromatic, aromatase, aromatherapy, etc.), marking chemical terms that begin with that prefix.

    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
    zilla
    -0.83
    放題
    -0.79
     firebaseConfig
    -0.78
    Palindrome
    -0.75
     zuhause
    -0.75
    CharSequence
    -0.74
     Katalog
    -0.73
     Creat
    -0.73
     Careers
    -0.72
     bors
    -0.72
    POSITIVE LOGITS
     аро
    0.83
    vaná
    0.79
    mord
    0.73
    扑
    0.72
     нега
    0.72
     falta
    0.71
    ânico
    0.70
     Gis
    0.69
     Aggregation
    0.69
     vow
    0.68
    Activations Density 0.029%

    No Known Activations