© 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. 103184
    Prev
    Next
    INDEX
    Explanations

    technical terms and compounds

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

    technical or scientific terminology across various domains like computing, medicine, and engineering.

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

    The neuron detects long, specialized multi‐syllable terms and proper names—i.e. technical or domain‐specific jargon.

    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
     sizable
    -1.02
     this
    -0.99
     strives
    -0.97
     striving
    -0.96
     low
    -0.96
     spurred
    -0.93
     an
    -0.91
     stating
    -0.90
     small
    -0.90
     substantial
    -0.89
    POSITIVE LOGITS
     jornalista
    1.12
     brillant
    1.11
     incredi
    1.05
    ECAUSE
    1.02
     Dateien
    1.01
    particularly
    1.00
    <bos>
    0.97
     ue
    0.96
     lamentable
    0.94
     proponent
    0.94
    Activations Density 0.880%

    No Known Activations