© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1895
    Prev
    Next
    INDEX
    Explanations

    buy items or services

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

    The neuron primarily fires on common English function words (especially short prepositions and articles such as “in,” “on,” “to,” “a,” 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
     contund
    -0.96
     colgar
    -0.94
    annt
    -0.91
    鉿
    -0.89
    عرِّف
    -0.88
     Viitattu
    -0.87
     fuertemente
    -0.85
    began
    -0.85
    掸
    -0.85
    bex
    -0.85
    POSITIVE LOGITS
    <b>
    1.34
    <strong>
    1.33
     womens
    1.17
     cheap
    1.12
    <u>
    1.12
     {{
    1.11
     menyen
    1.11
     jelasnya
    1.11
     legenda
    1.06
     Oklahoma
    1.05
    Activations Density 0.216%

    No Known Activations