© 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. 108109
    Prev
    Next
    INDEX
    Explanations

    linguistic features and languages

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

    The neuron fires on technical linguistic‐typology terms and headings (e.g. “linguistic typology,” “cross‐linguistic variation,” “morphological type,” “constituent order,” etc.).

    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
    Rost
    -0.75
    🗼
    -0.74
     Rubens
    -0.73
    威力
    -0.70
    ania
    -0.70
    է
    -0.70
    LOOKUP
    -0.70
    Kond
    -0.70
    RAI
    -0.67
    DotNetBar
    -0.67
    POSITIVE LOGITS
     languages
    0.89
     clauses
    0.83
    Proto
    0.82
     sentence
    0.81
     clause
    0.81
     erg
    0.78
    Position
    0.77
     serial
    0.77
    Kam
    0.76
    Experienced
    0.76
    Activations Density 0.052%

    No Known Activations