© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47063
    Prev
    Next
    INDEX
    Explanations

    quantities

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

    The neuron fires on colloquial intensifier or hedging words (e.g. “real,” “fer real,” “might,” “also”) that add emphasis or qualification.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ="_
    -0.94
     akan
    -0.86
    ]|
    -0.85
     yıl
    -0.81
    ַּ
    -0.79
    abile
    -0.79
     обору
    -0.79
    ас
    -0.79
     NOTHING
    -0.77
     atento
    -0.77
    POSITIVE LOGITS
    sies
    1.80
     muchas
    1.17
    sie
    1.07
     muitas
    1.06
     algunas
    1.02
     numero
    1.02
    Numero
    1.01
     meskipun
    0.98
     Numero
    0.98
     muchos
    0.96
    Activations Density 0.120%

    No Known Activations